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

    Neuronpedia

    INDEX
    Explanations

    words related to knowing a state, level, or how much you know

    oai_token-act-pair · gemini-2.0-flash

    conditions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    where
    -0.92
     
    -0.79
     where
    -0.78
    .
    -0.70
    Where
    -0.68
    ↵↵
    -0.67
    that
    -0.67
     the
    -0.64
    <eos>
    -0.63
     a
    -0.62
    POSITIVE LOGITS
     للمعارف
    1.31
     المعيارى
    1.26
     للاسماء
    1.25
     مرئيه
    1.23
     Normdatei
    1.22
     utafitiHapana
    1.21
     otomatig
    1.20
    expandindo
    1.17
    новниш
    1.16
    UrlResolution
    1.14
    Act Density 0.900%

    No Known Activations