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

    Neuronpedia

    INDEX
    Explanations

    topics and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     स्रो
    0.48
    我对
    0.45
    Ble
    0.45
    บริการ
    0.44
    Hình
    0.44
    我相信
    0.44
    姮
    0.44
    Non
    0.43
    亚
    0.42
    ifik
    0.41
    POSITIVE LOGITS
    ках
    0.48
     rendement
    0.44
    k
    0.44
     genomes
    0.43
     ਅ
    0.40
    kij
    0.40
     nuevos
    0.40
    dah
    0.39
     этому
    0.39
    gger
    0.39
    Act Density 0.001%

    No Known Activations