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

    Neuronpedia

    INDEX
    Explanations

    actual results may vary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Uno
    0.97
    rotating
    0.94
    preserving
    0.92
    Primer
    0.91
     lenguaje
    0.91
    Rotating
    0.91
    pushButton
    0.89
    Flat
    0.89
    previous
    0.88
    primer
    0.88
    POSITIVE LOGITS
    }|\
    0.95
    ıl
    0.88
     Cri
    0.86
     bhith
    0.83
     приз
    0.82
     authorizes
    0.80
     đòi
    0.79
    :_
    0.79
     ou
    0.79
    ☆
    0.78
    Act Density 0.004%

    No Known Activations