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

    Neuronpedia

    INDEX
    Explanations

    middleware, callbacks, promises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ойнотуу
    0.41
    SCHRAMM
    0.41
    льку
    0.41
    CommandHandler
    0.41
    臂
    0.40
    ╕
    0.40
     analyst
    0.40
    älle
    0.39
     PHILLIPS
    0.39
    :[/
    0.39
    POSITIVE LOGITS
    фа
    0.43
    пер
    0.42
    (
    0.41
    є
    0.41
    (-
    0.40
    ((
    0.39
    r
    0.39
    ({
    0.38
    dual
    0.38
    ([
    0.37
    Act Density 0.006%

    No Known Activations