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

    Neuronpedia

    INDEX
    Explanations

    comma operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hö
    0.43
    Addr
    0.43
     ответ
    0.42
    Breaking
    0.41
    Sé
    0.41
    一
    0.41
    大
    0.41
    idity
    0.40
     все
    0.39
    姆
    0.39
    POSITIVE LOGITS
     Metallic
    0.52
     Crus
    0.50
    <unused344>
    0.50
     വേദ
    0.49
     Machinist
    0.48
     Mosc
    0.48
    پيديا
    0.48
     fais
    0.47
     juc
    0.47
     Contest
    0.46
    Act Density 0.006%

    No Known Activations