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

    Neuronpedia

    INDEX
    Explanations

    math blackboard bold symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ع
    1.06
    이지만
    0.96
     ở
    0.95
    ا
    0.91
    މ
    0.89
    مي
    0.89
     of
    0.89
     αλλά
    0.88
    bears
    0.88
    ycles
    0.88
    POSITIVE LOGITS
     processor
    0.73
    ้อน
    0.66
    mathbf
    0.65
     hasattr
    0.64
     broker
    0.63
    il
    0.63
    н
    0.60
     DateTime
    0.59
     disallowed
    0.59
     class
    0.59
    Act Density 0.003%

    No Known Activations