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

    Neuronpedia

    INDEX
    Explanations

    return keyword

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    om
    1.10
    ép
    1.10
    uto
    0.96
    }{$\
    0.95
    ty
    0.94
    జ
    0.94
    uc
    0.93
    ä
    0.93
    isn
    0.93
    ów
    0.92
    POSITIVE LOGITS
     LOTRAchievement
    1.47
     semula
    1.12
     triun
    1.11
     nisi
    1.11
     BatchNorm
    1.10
     MaterialApp
    1.09
     jsonify
    1.08
     gulp
    1.08
     veineux
    1.07
    edDevice
    1.07
    Act Density 0.092%

    No Known Activations