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

    Neuronpedia

    INDEX
    Explanations

    curly brackets indicating code blocks

    oai_token-act-pair · gemini-2.0-flash

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }}$}
    -0.91
     Diſ
    -0.91
     ſtate
    -0.90
     purpoſe
    -0.88
    "]
    -0.87
     ftate
    -0.86
     ſch
    -0.84
    __(/*!
    -0.83
    ".
    -0.83
     ſeveral
    -0.82
    POSITIVE LOGITS
    <bos>
    1.32
    ↵↵
    0.84
    ↵
    0.63
    [
    0.60
    ’
    0.59
    mybatisplus
    0.56
    /
    0.54
     kasarigan
    0.52
    https
    0.50
    -
    0.48
    Act Density 0.766%

    No Known Activations