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

    Neuronpedia

    INDEX
    Explanations

    configuration arguments and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Unternehmens
    0.41
     Amber
    0.41
     UTM
    0.39
     ANSI
    0.38
     dễ
    0.38
     SM
    0.37
     Pfl
    0.37
     DMF
    0.37
     Obit
    0.37
     Cumberland
    0.36
    POSITIVE LOGITS
    enabled
    0.41
    args
    0.41
    参数
    0.40
    target
    0.40
    description
    0.40
     precedence
    0.39
    參數
    0.39
    얏
    0.38
    \]
    0.38
    }]
    0.38
    Act Density 0.018%

    No Known Activations