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

    Neuronpedia

    INDEX
    Explanations

    high

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     않
    -0.07
    esti
    -0.07
    William
    -0.07
    layan
    -0.07
    919
    -0.07
    _human
    -0.06
    .Then
    -0.06
     المف
    -0.06
    634
    -0.06
    osta
    -0.06
    POSITIVE LOGITS
    .navigationItem
    0.06
     asynchronous
    0.06
     حافظه
    0.06
    ‌پدی
    0.06
    ��
    0.06
    tık
    0.06
     џ
    0.06
    ancellation
    0.06
     �
    0.06
     Script
    0.05
    Act Density 0.017%

    No Known Activations