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

    Neuronpedia

    INDEX
    Explanations

    discussing or leading into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंखला
    0.85
    沄
    0.83
     рамках
    0.83
     встроен
    0.83
     avaliação
    0.83
     kondisi
    0.82
    ഴും
    0.81
     wyniku
    0.81
     pomocí
    0.80
    طيني
    0.80
    POSITIVE LOGITS
     or
    0.94
     calves
    0.93
     whenever
    0.92
     of
    0.92
    '."
    0.92
     wandering
    0.92
     -
    0.87
     lol
    0.86
    หรือ
    0.85
     who
    0.85
    Act Density 0.000%

    No Known Activations