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

    Neuronpedia

    INDEX
    Explanations

    HTML header tags to identify structural elements in a document

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

    software updates, release notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.52
     igen
    -0.42
    ffix
    -0.42
    rels
    -0.42
    UPAC
    -0.41
    GeoNames
    -0.40
    ForValue
    -0.39
     elems
    -0.38
     verrez
    -0.38
    GTCX
    -0.36
    POSITIVE LOGITS
     Wikiseite
    0.53
     Grüsse
    0.51
    Personensuche
    0.51
     مرئيه
    0.50
     wikipagina
    0.50
     Könige
    0.49
    Välislingid
    0.48
    enumii
    0.47
     nakalista
    0.47
    ]")]
    0.47
    Act Density 0.047%

    No Known Activations