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

    Neuronpedia

    INDEX
    Explanations

    be beautiful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ই
    1.04
    وره
    0.97
    ت
    0.95
    کش
    0.93
    e
    0.92
     عج
    0.90
    Resistance
    0.88
    cón
    0.87
     মন
    0.87
    दे
    0.86
    POSITIVE LOGITS
    autiful
    1.48
    headed
    1.45
    comes
    1.39
    ulah
    1.38
    acuse
    1.36
    headings
    1.36
    WEEN
    1.27
    缚
    1.24
    ভূমিতে
    1.19
    fits
    1.19
    Act Density 0.146%

    No Known Activations