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

    Neuronpedia

    INDEX
    Explanations

    British

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Utf
    -0.08
     Bet
    -0.07
    	can
    -0.06
    _builtin
    -0.06
    تصريح
    -0.06
    osta
    -0.06
     وما
    -0.06
     мат
    -0.06
    ۇ
    -0.06
     בעבר
    -0.06
    POSITIVE LOGITS
    填写
    0.08
    -messages
    0.07
    LECTION
    0.07
    -training
    0.07
    _CHK
    0.07
    history
    0.07
    .textField
    0.07
    minute
    0.07
    pageNum
    0.07
     maximum
    0.06
    Act Density 0.285%

    No Known Activations