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

    Neuronpedia

    INDEX
    Explanations

    expressing thoughts or beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ات
    1.23
    確認
    1.07
    ları
    1.04
     Обычно
    1.03
    偣
    1.02
     horn
    0.98
     thick
    0.96
     mouth
    0.96
    鋯
    0.95
    ность
    0.94
    POSITIVE LOGITS
    م
    1.35
    homeini
    1.13
    शील
    1.10
    వంత
    1.10
     byť
    1.05
    هه
    1.05
    TimeSeries
    1.04
     findViewById
    1.04
    शीलता
    1.04
    هُ
    1.01
    Act Density 0.245%

    No Known Activations