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

    Neuronpedia

    INDEX
    Explanations

    please refer, told stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    no
    0.85
     engagements
    0.84
    MAS
    0.81
     affections
    0.79
    ing
    0.78
    но
    0.78
    teeth
    0.78
    ষ্ট্র
    0.77
    ings
    0.76
    ements
    0.73
    POSITIVE LOGITS
    cg
    0.87
    導數
    0.86
    𝙖
    0.84
    )$;
    0.84
    apayati
    0.80
    ciones
    0.79
    เร็จ
    0.78
     гульнявыя
    0.76
    sessionId
    0.76
     ترتیب
    0.76
    Act Density 0.000%

    No Known Activations