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

    Neuronpedia

    INDEX
    Explanations

    headings and structural elements of the document

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

    HTML heading tag "<h4>"

    np_acts-logits-general · gemini-2.0-flash

    commercial implementations following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.86
    ContentAsync
    -0.86
     للاسماء
    -0.67
    ==",
    -0.65
    исленность
    -0.64
    PreferredItem
    -0.63
    TypedDataSet
    -0.63
    ")->
    -0.61
    ",$
    -0.60
    localctx
    -0.60
    POSITIVE LOGITS
    <h4>
    0.80
    imageshack
    0.64
    <h5>
    0.60
    }*/
    0.56
    </h4>
    0.53
    </h5>
    0.50
    Fehler
    0.50
    luia
    0.49
    hoga
    0.47
     esegu
    0.47
    Act Density 0.045%

    No Known Activations