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

    Neuronpedia

    INDEX
    Explanations

    Nintendo Switch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    1.09
     in
    1.05
    o
    0.91
    ry
    0.85
    s
    0.85
    !
    0.82
     o
    0.81
    :
    0.80
    ?
    0.79
    _
    0.78
    POSITIVE LOGITS
     Setelah
    0.78
     Setiap
    0.74
     Während
    0.74
     Nintendo
    0.73
     Podczas
    0.73
    ன
    0.72
     Mozilla
    0.70
    撣
    0.70
     Wii
    0.70
    Nintendo
    0.70
    Act Density 0.003%

    No Known Activations