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

    Neuronpedia

    INDEX
    Explanations

    Greek letters, code, and currency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    卸
    0.39
    isent
    0.38
    wol
    0.37
    CTG
    0.37
    wal
    0.36
     سازمان
    0.36
    pry
    0.36
    caret
    0.35
     नाग
    0.35
    pow
    0.35
    POSITIVE LOGITS
     Endocrinol
    0.45
     Eliz
    0.44
    佶
    0.43
     ভু
    0.42
     marvell
    0.40
     கிறிஸ்துவின்
    0.40
    佾
    0.39
     पादु
    0.39
     훨
    0.39
     Liz
    0.38
    Act Density 0.000%

    No Known Activations