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

    Neuronpedia

    INDEX
    Explanations

    emphasis characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prov
    -0.08
    。
    -0.07
    برز
    -0.07
    Have
    -0.07
    :
    -0.07
    ระ
    -0.07
    _param
    -0.07
    �
    -0.06
     הנה
    -0.06
    _Item
    -0.06
    POSITIVE LOGITS
    queda
    0.07
    imonial
    0.07
    פחות
    0.06
     forState
    0.06
     数据
    0.06
    LED
    0.06
    从而使
    0.06
     sleek
    0.06
    TableName
    0.06
     ));
    0.06
    Act Density 0.044%

    No Known Activations