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

    Neuronpedia

    INDEX
    Explanations

    sorrow dwells

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ক
    0.96
    otry
    0.83
    ب
    0.82
    ak
    0.81
    ogy
    0.78
    ब
    0.77
     brownies
    0.76
    it
    0.75
    না
    0.75
    به
    0.75
    POSITIVE LOGITS
    تي
    0.96
    ви
    0.95
     нажа
    0.95
    resolved
    0.92
    пробу
    0.91
    writeFile
    0.91
    rejected
    0.89
     floated
    0.88
     moze
    0.88
    াৰ
    0.88
    Act Density 0.002%

    No Known Activations