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

    Neuronpedia

    INDEX
    Explanations

    array handling in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     聞い
    0.57
    essing
    0.52
     웨
    0.50
    essed
    0.48
    drums
    0.48
    iterranean
    0.47
     sagittis
    0.47
     tendances
    0.47
    essi
    0.47
    law
    0.46
    POSITIVE LOGITS
    вана
    0.55
     Eltern
    0.49
    発見
    0.47
    偶然
    0.47
    اق
    0.46
    取り
    0.46
     tə
    0.46
    </h3>
    0.46
    อกาส
    0.46
    知道
    0.44
    Act Density 0.000%

    No Known Activations