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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _mutex
    -0.07
    رف
    -0.07
    茨
    -0.07
     Walters
    -0.07
    _ij
    -0.06
     trench
    -0.06
     gel
    -0.06
    鱼
    -0.06
    -0.06
    фф
    -0.06
    POSITIVE LOGITS
     záb
    0.06
     honoured
    0.06
    (item
    0.06
     Cumhurbaşkanı
    0.06
    idual
    0.06
    .asInstanceOf
    0.06
     shooter
    0.06
     impunity
    0.06
     shards
    0.06
     priorit
    0.06
    Act Density 0.026%

    No Known Activations