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

    Neuronpedia

    INDEX
    Explanations

    fast, poor, speed, trade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poiché
    0.58
    s
    0.55
    ים
    0.55
    ي
    0.55
     accessor
    0.53
    uuuu
    0.53
    తో
    0.52
    ઓની
    0.52
     एकजुट
    0.52
    ঠু
    0.52
    POSITIVE LOGITS
    LDA
    0.49
    I
    0.46
    льше
    0.45
    ubahan
    0.45
    лью
    0.43
    Luke
    0.43
    LR
    0.43
    isho
    0.42
    AuditEvent
    0.42
    levision
    0.41
    Act Density 0.000%

    No Known Activations