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

    Neuronpedia

    INDEX
    Explanations

    square brackets, code snippets, and database-related words

    oai_token-act-pair · gemini-2.0-flash

    math or code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.83
     Paglinawan
    -0.81
     Signalez
    -0.69
    loài
    -0.68
    GraphicsUnit
    -0.67
    tvguidetime
    -0.65
    onView
    -0.65
    nswer
    -0.65
    */;
    -0.64
    berdayakan
    -0.61
    POSITIVE LOGITS
    '
    0.76
    "
    0.67
    Obrázky
    0.66
    ↵
    0.64
    <bos>
    0.63
    ChildScrollView
    0.63
    ’
    0.60
    \
    0.59
    {
    0.59
    .
    0.58
    Act Density 11.374%

    No Known Activations