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

    Neuronpedia

    INDEX
    Explanations

    URLs and related text

    oai_token-act-pair · gemini-2.0-flash

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.79
    ↵
    -0.63
     of
    -0.60
    :
    -0.57
    "
    -0.54
    The
    -0.52
    D
    -0.52
    /
    -0.52
    </h2>
    -0.52
    </i>
    -0.52
    POSITIVE LOGITS
    ⓧ
    1.43
    Autoritní
    1.33
    NameInMap
    1.27
    MigrationBuilder
    1.23
     estekak
    1.19
    IUrlHelper
    1.19
     auffi
    1.15
    LookAnd
    1.15
     tartalomajánló
    1.11
     myſelf
    1.09
    Act Density 2.661%

    No Known Activations