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

    Neuronpedia

    INDEX
    Explanations

    names and descriptive labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utz
    0.43
    ño
    0.41
    yu
    0.40
    ay
    0.40
    aceted
    0.40
     MAINTENANCE
    0.40
    ienka
    0.39
    oyin
    0.38
    ostino
    0.38
    acán
    0.37
    POSITIVE LOGITS
    зер
    0.42
     Bead
    0.38
    㳑
    0.35
     intermediates
    0.35
    吩
    0.35
    传感器
    0.35
     Бе
    0.34
     rozgry
    0.34
    ాల్
    0.34
     Lect
    0.34
    Act Density 0.000%

    No Known Activations