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

    Neuronpedia

    INDEX
    Explanations

    MY App Time 6

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     k
    0.61
     ہماری
    0.57
    <unused81>
    0.56
     انتہائی
    0.56
    ⁶
    0.55
    蝎
    0.54
     仕事
    0.54
     പോക
    0.54
     arrogance
    0.53
     အမျိုး
    0.53
    POSITIVE LOGITS
    d
    0.85
    ే
    0.73
    as
    0.68
    د
    0.67
    elijke
    0.64
    中
    0.62
    دة
    0.59
    en
    0.58
    लेन
    0.58
    इसके
    0.56
    Act Density 0.000%

    No Known Activations