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

    Neuronpedia

    INDEX
    Explanations

    factual information

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    osław
    0.66
     SINGLE
    0.61
    を変更
    0.59
    cron
    0.57
    ſs
    0.56
     eius
    0.55
     Gericht
    0.55
    ผสม
    0.55
    sprogram
    0.54
     COPY
    0.54
    POSITIVE LOGITS
     wax
    0.64
    туры
    0.62
    础
    0.57
    伟
    0.56
     vented
    0.55
     lifetimes
    0.53
    發
    0.53
     무료
    0.53
    Lifetime
    0.52
     prominence
    0.52
    Act Density 0.000%

    No Known Activations