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

    Neuronpedia

    INDEX
    Explanations

    harmful content or violations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ändern
    0.48
     Refunds
    0.43
    kaan
    0.43
     मिड
    0.42
    yCoordinate
    0.42
    cents
    0.42
     refunds
    0.42
    liği
    0.42
     oscillators
    0.42
    እንደ
    0.42
    POSITIVE LOGITS
     KPI
    0.45
     TRPV
    0.45
     lod
    0.45
     شبه
    0.44
     nguy
    0.44
     cung
    0.44
    ين
    0.42
    局面
    0.42
    羈
    0.42
     Reino
    0.42
    Act Density 0.004%

    No Known Activations