Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Reviews and descriptions

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of “hand”–prefixed words (e.g., handwritten, hand-assembled) referring to manually made or written items.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    mentions of content or tangible media items (e.g., notes, cards, screens, laptops) and related content-related terms.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    เหล
    -0.06
    Ord
    -0.06
    .circular
    -0.06
    .parts
    -0.06
     Cry
    -0.06
    $args
    -0.06
     조금
    -0.06
    .OP
    -0.06
     Job
    -0.06
     квіт
    -0.06
    POSITIVE LOGITS
     entitlement
    0.07
     než
    0.07
     physique
    0.07
     сло
    0.06
    pedo
    0.06
    licity
    0.06
    UTILITY
    0.06
    prediction
    0.06
    nearest
    0.06
    reak
    0.06
    Act Density 0.472%

    No Known Activations