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

    Neuronpedia

    INDEX
    Explanations

    references to figures and tables in the document

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

    figures or tables

    np_acts-logits-general · gemini-2.0-flash

    figure, table, and proof citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #+#
    -0.65
    TagMode
    -0.56
    httphttps
    -0.53
    帖最后由
    -0.53
    rungsseite
    -0.52
     հղումներ
    -0.51
     otomatig
    -0.50
    }*/
    -0.50
     Chwiliwch
    -0.50
    MigrationBuilder
    -0.50
    POSITIVE LOGITS
    </strong>
    0.55
    </b>
    0.52
     enc
    0.38
     fol
    0.37
     investi
    0.35
     سم
    0.35
     acci
    0.34
    WRENCE
    0.33
    timewa
    0.32
     Requis
    0.32
    Act Density 0.399%

    No Known Activations