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

    Neuronpedia

    INDEX
    Explanations

    pulses, sharpened, deposit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    currently
    0.92
     currently
    0.90
     lige
    0.86
    जो
    0.85
    ಕ್ರಮ
    0.84
    ğinin
    0.84
     викона
    0.84
    蒡
    0.83
     borde
    0.82
    ostante
    0.82
    POSITIVE LOGITS
    Haha
    1.50
     "@{
    1.31
     Haha
    1.29
     Lender
    1.29
     violin
    1.29
     Они
    1.28
     HOMO
    1.22
    िक
    1.20
     ప్రేమ
    1.20
    垚
    1.19
    Act Density 0.002%

    No Known Activations