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

    Neuronpedia

    INDEX
    Explanations

    position

    np_max-act · gemini-2.0-flash

    phrases indicating authority dynamics and power imbalances in interpersonal interactions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ta
    -0.07
    小说
    -0.07
     tặng
    -0.07
     Reduction
    -0.06
     vàng
    -0.06
    GenericType
    -0.06
    師
    -0.06
     toured
    -0.06
     substance
    -0.06
     mathematics
    -0.06
    POSITIVE LOGITS
    (parent
    0.07
    _web
    0.06
    "?↵↵
    0.06
     zih
    0.06
    .clicked
    0.06
    oler
    0.06
     Stuttgart
    0.06
    ूसर
    0.06
    !
↵
    0.06
     divine
    0.06
    Act Density 0.016%

    No Known Activations