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

    Neuronpedia

    INDEX
    Explanations

    the equals sign and code loop syntax, especially involving the variable `i`

    oai_token-act-pair · gemini-2.0-flash

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.79
    <bos>
    -0.79
     CreateTagHelper
    -0.78
     ddelweddau
    -0.72
     Wiktionnaire
    -0.71
    Gweler
    -0.70
     الرياضيه
    -0.66
     سكانية
    -0.65
    toMatchSnapshot
    -0.65
     entière
    -0.60
    POSITIVE LOGITS
     hanggang
    0.53
    setDo
    0.50
    φό
    0.47
    Apro
    0.46
     الاطلاع
    0.46
     middle
    0.46
     Warum
    0.44
    álního
    0.44
    JMenuItem
    0.44
    veen
    0.43
    Act Density 0.496%

    No Known Activations