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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols, notations, and references related to matrices and computational graphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    each item or grouping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.82
     surla
    -0.74
    WriteAttribute
    -0.74
     disambiguazione
    -0.73
    DockStyle
    -0.72
     ब्रेकडाउन
    -0.72
    AddTagHelper
    -0.71
    enterOuterAlt
    -0.70
     snippetHide
    -0.70
    twimg
    -0.69
    POSITIVE LOGITS
     each
    0.37
    各自
    0.35
     om
    0.33
     driven
    0.33
    setz
    0.33
     para
    0.32
     Each
    0.32
     σω
    0.31
     hver
    0.30
     équip
    0.30
    Act Density 0.299%

    No Known Activations