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

    Neuronpedia

    INDEX
    Explanations

    introducing code or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $
    1.03
    й
    0.99
    i
    0.94
     gearing
    0.92
    o
    0.92
    ‘
    0.86
    “…
    0.83
    𝑛
    0.82
    y
    0.82
    ة
    0.82
    POSITIVE LOGITS
    ৬
    1.13
    ̮
    1.09
    ."),
    0.96
    啪
    0.96
    АР
    0.96
    }"),
    0.95
    httphttps
    0.95
    燬
    0.93
    ש
    0.93
    retry
    0.93
    Act Density 0.748%

    No Known Activations