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

    Neuronpedia

    INDEX
    Explanations

    SU, BE, DE, SE, MO, AN, TR, MO, EX, SO

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ş
    0.49
    ătoare
    0.47
    şk
    0.44
    țin
    0.43
    ătur
    0.42
    ị
    0.41
    ပိုင်း
    0.41
    ón
    0.40
    ovací
    0.40
    nički
    0.39
    POSITIVE LOGITS
    ORY
    0.63
    RE
    0.62
    AN
    0.61
    ER
    0.61
    UR
    0.59
    ON
    0.59
    IN
    0.59
    ATT
    0.59
    INA
    0.57
    AR
    0.55
    Act Density 0.031%

    No Known Activations