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

    Neuronpedia

    INDEX
    Explanations

    Oil inspections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jaar
    0.84
     thưởng
    0.79
    iya
    0.77
    iw
    0.77
    登上
    0.76
    ‹
    0.76
    uyên
    0.75
    atre
    0.75
    重量
    0.73
    但也
    0.73
    POSITIVE LOGITS
    ة
    0.85
    Clique
    0.74
     Бы
    0.73
    Semit
    0.73
    Elvis
    0.73
     IGBT
    0.73
     competente
    0.72
     BCH
    0.70
    гляда
    0.70
     Agus
    0.70
    Act Density 0.002%

    No Known Activations