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

    Neuronpedia

    INDEX
    Explanations

    i am programmed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    т
    1.93
    ن
    1.69
    sächlich
    1.48
     Crops
    1.46
     cuisines
    1.45
     deja
    1.41
     Careful
    1.41
    에요
    1.38
    screw
    1.37
     udah
    1.32
    POSITIVE LOGITS
    ă
    2.19
    ів
    2.08
    ı
    2.06
    ıya
    1.98
    ü
    1.95
    ㈡
    1.88
    客様
    1.85
    હુ
    1.79
    í
    1.79
    ת
    1.73
    Act Density 0.453%

    No Known Activations