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

    Neuronpedia

    INDEX
    Explanations

    due

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wenige
    0.97
    ց
    0.91
    venidos
    0.90
    als
    0.89
    xious
    0.89
     vorher
    0.88
     millilit
    0.87
    featuring
    0.87
    priced
    0.86
     verpflicht
    0.86
    POSITIVE LOGITS
    ی
    0.90
    ก
    0.90
    }");
    0.86
    مر
    0.82
    みました
    0.82
    ક
    0.82
    우
    0.79
    ب
    0.79
    ই
    0.76
    చే
    0.75
    Act Density 0.001%

    No Known Activations