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

    Neuronpedia

    INDEX
    Explanations

    embedded systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ている
    1.49
    δήποτε
    1.48
     shears
    1.45
    с
    1.35
    it
    1.34
    ্স
    1.34
    をする
    1.33
    ても
    1.30
    clientX
    1.30
    스
    1.28
    POSITIVE LOGITS
    Н
    2.06
    t
    1.90
    smanship
    1.82
    И
    1.74
    speople
    1.73
    tod
    1.66
    Б
    1.65
    tul
    1.59
    О
    1.56
    số
    1.55
    Act Density 0.064%

    No Known Activations