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

    Neuronpedia

    INDEX
    Explanations

    words and phrases commonly found in academic papers

    oai_token-act-pair · gemini-2.0-flash

    Instructions and definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.86
    <bos>
    -0.84
    TypedDataSet
    -0.80
     autorytatywna
    -0.75
    ValueStyle
    -0.68
    migrationBuilder
    -0.67
    :✨
    -0.63
    tagext
    -0.58
    Geplaatst
    -0.57
    Bibliograf
    -0.55
    POSITIVE LOGITS
     themſelves
    0.60
     greateſt
    0.59
     himſelf
    0.59
    AxisAlignment
    0.58
     Efq
    0.57
    alnız
    0.56
    InputBorder
    0.56
     poffe
    0.54
    qtype
    0.54
     Theſe
    0.54
    Act Density 13.260%

    No Known Activations