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

    Neuronpedia

    INDEX
    Explanations

    code blocks and numbering within those blocks.

    oai_token-act-pair · gemini-2.0-flash

    Number one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مشين
    -0.72
     ""],
    -0.68
     CURIAM
    -0.66
    transQ
    -0.60
    <bos>
    -0.60
     NSCoder
    -0.59
    CloseOperation
    -0.58
     himo
    -0.57
     TextAppearance
    -0.57
    orElseThrow
    -0.56
    POSITIVE LOGITS
    nito
    0.50
    uffff
    0.46
    rettet
    0.46
     NBS
    0.45
    salm
    0.44
     view
    0.44
     hembra
    0.43
    view
    0.43
    faat
    0.42
    zydent
    0.42
    Act Density 2.166%

    No Known Activations