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

    Neuronpedia

    INDEX
    Explanations

    benign or malignant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arlık
    0.46
     위의
    0.42
    cké
    0.41
    èrement
    0.41
    锌
    0.41
     комиссии
    0.41
     ойнотуу
    0.40
     കിട
    0.40
     trauer
    0.40
     क्ष
    0.39
    POSITIVE LOGITS
    Revolution
    0.43
    October
    0.42
     revolution
    0.40
     Revolution
    0.39
     cy
    0.38
     cosmopolitan
    0.38
    gdf
    0.38
     molecular
    0.38
     October
    0.37
    Molecular
    0.37
    Act Density 0.006%

    No Known Activations