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

    Neuronpedia

    INDEX
    Explanations

    sending data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ות
    0.57
    acán
    0.48
    ോള
    0.46
    llll
    0.46
    ıt
    0.46
    ipino
    0.45
    셉
    0.45
    ời
    0.44
    öy
    0.44
    빅
    0.44
    POSITIVE LOGITS
     بالط
    0.44
     عام
    0.42
     penned
    0.42
    G
    0.42
     prolific
    0.40
    elift
    0.40
     އަ
    0.40
    yla
    0.39
    isel
    0.39
     dạ
    0.39
    Act Density 0.000%

    No Known Activations