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

    Neuronpedia

    INDEX
    Explanations

    sabotage and blend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.48
    a
    0.47
     upto
    0.45
    百姓
    0.45
    ten
    0.43
    ле
    0.43
    k
    0.43
     للا
    0.43
     Unterschiede
    0.42
     Up
    0.42
    POSITIVE LOGITS
    ໋
    0.49
     dimensionless
    0.44
    beren
    0.44
     सॉफ्टवेयर
    0.43
    ▿
    0.42
    ոն
    0.41
    0.41
     있는
    0.41
    ิ่ง
    0.41
    림
    0.41
    Act Density 0.005%

    No Known Activations