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

    Neuronpedia

    INDEX
    Explanations

    the word "every"

    oai_token-act-pair · gemini-2.0-flash

    every

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estekak
    -0.75
    AddHtmlAttribute
    -0.73
    ThroughAttribute
    -0.71
    WithIOException
    -0.64
     magari
    -0.63
     يتيمه
    -0.62
    =?,
    -0.62
     فريبيس
    -0.62
    IGraphics
    -0.62
    stylers
    -0.61
    POSITIVE LOGITS
    endregion
    0.50
    erschein
    0.47
     these
    0.45
    gink
    0.40
    وث
    0.40
    RELATIVE
    0.40
     Bourgoin
    0.39
    ết
    0.39
     nor
    0.39
     secretary
    0.38
    Act Density 1.457%

    No Known Activations