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

    Neuronpedia

    INDEX
    Explanations

    capitalized two-letter abbreviations, or the prefix "ante-", or parts of the name "Kyuban"

    oai_token-act-pair · gemini-2.0-flash

    proper nouns

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    OGND
    -0.63
    SourceChecksum
    -0.59
    expandindo
    -0.58
     defaultstate
    -0.56
     '\\;'
    -0.54
    väll
    -0.51
    riles
    -0.50
    ">—
    -0.50
     Efq
    -0.49
     Roskov
    -0.49
    POSITIVE LOGITS
    тний
    0.56
    AnchorStyles
    0.54
     Bors
    0.54
    mení
    0.52
     Himo
    0.51
    findpost
    0.50
    RTDA
    0.49
    ckel
    0.46
     soie
    0.45
    тини
    0.44
    Act Density 0.218%

    No Known Activations