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

    Neuronpedia

    INDEX
    Explanations

    slave

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     информации
    -0.07
     международ
    -0.07
    Aug
    -0.07
     assertion
    -0.07
    운동
    -0.07
     continuous
    -0.07
     economical
    -0.07
     Rodrig
    -0.07
     noon
    -0.07
     úkol
    -0.06
    POSITIVE LOGITS
     صاحب
    0.07
    �
    0.06
    虫
    0.06
     swallow
    0.06
    _filepath
    0.06
     Savage
    0.06
     Вс
    0.06
    الب
    0.06
    WS
    0.06
    Work
    0.06
    Act Density 0.008%

    No Known Activations