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

    Neuronpedia

    INDEX
    Explanations

    assignments and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     concentric
    0.65
     cô
    0.62
     관련
    0.62
     bridesmaids
    0.62
     параметра
    0.61
     hàm
    0.61
     언급
    0.60
     sling
    0.60
     použív
    0.60
     แบบ
    0.60
    POSITIVE LOGITS
    new
    0.80
    temps
    0.78
     nieuwe
    0.77
    新たな
    0.77
    Temp
    0.76
    Expenses
    0.76
     new
    0.76
    Tempor
    0.74
    Salle
    0.74
    Dup
    0.70
    Act Density 0.840%

    No Known Activations