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

    Neuronpedia

    INDEX
    Explanations

    module definition or import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uous
    1.04
     nonradiative
    1.00
    寯
    1.00
    Це
    0.99
    氦
    0.99
    RawO
    0.98
    芻
    0.98
    柅
    0.97
     অর্থে
    0.94
    滈
    0.94
    POSITIVE LOGITS
    та
    1.21
    z
    1.20
    a
    1.06
    '
    1.03
    amp
    1.01
    b
    1.00
    au
    0.97
    ä
    0.94
    ite
    0.93
    es
    0.92
    Act Density 0.001%

    No Known Activations