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

    Neuronpedia

    INDEX
    Explanations

    making

    np_max-act · gemini-2.0-flash

    The neuron activates on past-tense verb tokens (e.g., “created,” “built,” “generated,” “made”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Sud
    -0.06
     trials
    -0.06
     prominent
    -0.06
     bdsm
    -0.06
     commanders
    -0.06
    ashion
    -0.06
    -filter
    -0.06
     parece
    -0.06
    .mime
    -0.06
    -ring
    -0.06
    POSITIVE LOGITS
    .Col
    0.07
     mẽ
    0.07
    ”?
    0.07
     Ã
    0.07
     तरफ
    0.06
    .")
    0.06
     swirling
    0.06
    ية
    0.06
    ')==
    0.06
    .'"
    0.06
    Act Density 0.031%

    No Known Activations