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

    Neuronpedia

    INDEX
    Explanations

    virtual DOM and folders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ר
    0.46
    ト
    0.44
    رر
    0.43
    ისა
    0.43
    τυ
    0.42
     MERCHANTABILITY
    0.42
    樂
    0.41
    கா
    0.41
    주의
    0.41
    Butyl
    0.41
    POSITIVE LOGITS
     让
    0.51
    stes
    0.48
     ملي
    0.47
    ique
    0.46
    este
    0.46
    alin
    0.46
     wsp
    0.46
    ouv
    0.45
    élève
    0.45
    就连
    0.45
    Act Density 0.000%

    No Known Activations