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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yoga
    -0.07
    ascus
    -0.06
    OSH
    -0.06
     FLAC
    -0.06
    uggestions
    -0.06
    _lm
    -0.06
     quizzes
    -0.06
    ();"
    -0.06
    ancellation
    -0.06
    Decl
    -0.06
    POSITIVE LOGITS
    多
    0.06
    為
    0.06
    )'↵
    0.06
    WN
    0.06
     возв
    0.06
     Пов
    0.06
     resides
    0.06
    ',{'
    0.06
     pleaded
    0.06
     Gilles
    0.06
    Act Density 0.000%

    No Known Activations