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

    Neuronpedia

    INDEX
    Explanations

    academic bibliography formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .InputStream
    -0.07
     attendees
    -0.06
     NEG
    -0.06
    ิท
    -0.06
     TextField
    -0.06
     Afro
    -0.06
     Welfare
    -0.06
    emia
    -0.06
     ».
    -0.06
     athlete
    -0.06
    POSITIVE LOGITS
    oundation
    0.07
     sympathy
    0.06
     Timestamp
    0.06
     дви
    0.06
    _bm
    0.06
    $body
    0.06
    ζα
    0.06
    账
    0.06
    hood
    0.06
    $model
    0.06
    Act Density 0.001%

    No Known Activations