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

    Neuronpedia

    INDEX
    Explanations

    Exercise frequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disability
    -0.07
     Candle
    -0.07
    כנע
    -0.07
     pack
    -0.07
    理科
    -0.07
     remember
    -0.07
     affid
    -0.07
     Fahrenheit
    -0.07
    偏低
    -0.07
    ��
    -0.07
    POSITIVE LOGITS
    زار
    0.08
    produto
    0.08
    �
    0.08
    _EXPR
    0.07
    礵
    0.07
     veel
    0.07
     즉
    0.07
    در
    0.07
     Algorithm
    0.07
    鹟
    0.07
    Act Density 0.013%

    No Known Activations