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

    Neuronpedia

    INDEX
    Explanations

    more and more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     other
    1.05
     more
    0.95
     form
    0.92
    ec
    0.88
     newer
    0.86
    other
    0.84
    form
    0.83
    ek
    0.83
    л
    0.80
     Other
    0.79
    POSITIVE LOGITS
    そして
    0.95
     tentatives
    0.93
    mäßige
    0.91
     बालकनियां
    0.86
     successive
    0.86
    gameOver
    0.84
    ❘
    0.83
     encuentros
    0.82
     zahlreiche
    0.82
     premieres
    0.81
    Act Density 0.056%

    No Known Activations