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

    Neuronpedia

    INDEX
    Explanations

    country of origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     önüne
    1.01
    ל
    0.93
    ясь
    0.90
    وں
    0.88
     germinate
    0.87
     looming
    0.85
     noqa
    0.85
    ژگی
    0.85
    লোড
    0.84
     случа
    0.83
    POSITIVE LOGITS
    dec
    0.94
    desde
    0.94
     aback
    0.92
    modulo
    0.89
    grad
    0.87
    try
    0.87
    dir
    0.86
     whence
    0.85
    deg
    0.82
    bulld
    0.82
    Act Density 0.009%

    No Known Activations