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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     theatrical
    -0.07
    社会各界
    -0.06
    あった
    -0.06
     armed
    -0.06
     autism
    -0.06
    .Children
    -0.06
     daddy
    -0.06
    qml
    -0.06
    /entities
    -0.06
    (mContext
    -0.06
    POSITIVE LOGITS
    垱
    0.07
    ilee
    0.07
     prayers
    0.07
    +s
    0.07
    入住
    0.07
    _pwd
    0.07
    _ylabel
    0.06
    _year
    0.06
     Free
    0.06
    (--
    0.06
    Act Density 0.006%

    No Known Activations