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

    Neuronpedia

    INDEX
    Explanations

    tragedy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.92
    ะ
    0.85
    is
    0.81
    ug
    0.81
    on
    0.79
     is
    0.78
    ग
    0.75
    ä
    0.74
    planetary
    0.73
    ਰ
    0.72
    POSITIVE LOGITS
    ك
    1.29
    لي
    1.08
     traged
    0.96
    ير
    0.92
     trag
    0.90
     tragedy
    0.86
     Иванов
    0.86
     tragedies
    0.85
     incremento
    0.85
    }";
    0.82
    Act Density 0.001%

    No Known Activations