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

    Neuronpedia

    INDEX
    Explanations

    unless the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comparing
    0.60
    ール
    0.55
     використа
    0.50
     immor
    0.50
     hausse
    0.49
    ハ
    0.47
     achter
    0.46
     overcast
    0.46
     dlatego
    0.46
     attacking
    0.45
    POSITIVE LOGITS
    )$;
    0.55
     کوډ
    0.54
    \}$.
    0.53
    oC
    0.47
    !);
    0.47
     ຊ
    0.46
    ){
    0.45
    okan
    0.45
    UserInput
    0.45
    XPath
    0.44
    Act Density 0.002%

    No Known Activations