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

    Neuronpedia

    INDEX
    Explanations

    presence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    절
    -0.06
    occer
    -0.06
    솔
    -0.06
    ед
    -0.06
     shl
    -0.06
    Bài
    -0.06
    OLUMN
    -0.06
    Cool
    -0.06
    AMED
    -0.06
    qual
    -0.06
    POSITIVE LOGITS
     Tories
    0.06
    _signed
    0.06
    maids
    0.06
    ۱۳۸
    0.06
    Duration
    0.06
     Fortress
    0.06
     توضی
    0.06
    ьв
    0.06
    (Object
    0.06
    inine
    0.06
    Act Density 0.009%

    No Known Activations