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

    Neuronpedia

    INDEX
    Explanations

    if statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺳ
    0.46
    ियोग
    0.39
    тальян
    0.39
    చ్చ
    0.38
    платы
    0.38
    Revenue
    0.38
    จุ
    0.38
     бри
    0.37
    وسف
    0.37
    觞
    0.36
    POSITIVE LOGITS
     !
    1.09
     !(
    0.93
     isinstance
    0.89
    (!
    0.83
     (!
    0.82
     hasattr
    0.78
     !$
    0.74
     !_
    0.72
    (!(
    0.70
     (!(
    0.70
    Act Density 0.030%

    No Known Activations