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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /include
    -0.07
    Unhandled
    -0.07
     kaynak
    -0.07
    ckpt
    -0.06
    ふ
    -0.06
     시스템
    -0.06
    'image
    -0.06
    _PRI
    -0.06
    ments
    -0.06
     UIAlertView
    -0.06
    POSITIVE LOGITS
     ValueType
    0.07
     기준
    0.07
     humiliating
    0.07
     local
    0.07
    neck
    0.07
    ụy
    0.07
    Anna
    0.06
    sov
    0.06
    ुत
    0.06
     sitting
    0.06
    Act Density 0.002%

    No Known Activations