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

    Neuronpedia

    INDEX
    Explanations

    organization names and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    0.73
    im
    0.61
    ap
    0.61
    ون
    0.58
    ه‌ای
    0.58
    ys
    0.58
    oc
    0.57
    ческие
    0.55
    یر
    0.55
    ce
    0.54
    POSITIVE LOGITS
    นิด
    0.57
     kritis
    0.55
     eftersom
    0.54
    ଡ
    0.54
    лото
    0.53
     налич
    0.52
    үн
    0.52
     със
    0.52
     süt
    0.51
     sozialen
    0.51
    Act Density 0.007%

    No Known Activations