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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations and results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    1.66
    ,
    1.61
    -
    1.52
    "
    1.51
    .
    1.46
    $
    1.37
    )
    1.29
    \
    1.28
    {
    1.19
    /
    1.14
    POSITIVE LOGITS
    。「
    0.96
    ։
    0.96
    ++.
    0.96
    。」
    0.93
     oxidación
    0.88
    ='/
    0.86
    နစ်
    0.84
    ².
    0.81
     ಜಿಲ್ಲ
    0.80
    %.
    0.80
    Act Density 0.751%

    No Known Activations