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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting related to programming or mathematical expressions

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

    SELECT * meaning All

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rativa
    -0.44
     giudice
    -0.43
     umana
    -0.41
     bodas
    -0.41
    inguém
    -0.41
    avelmente
    -0.40
    inata
    -0.39
     EPA
    -0.38
     Grüsse
    -0.38
     plátano
    -0.38
    POSITIVE LOGITS
     мәкал
    0.64
     Administrativna
    0.59
    star
    0.59
    *>
    0.56
    Rhestr
    0.55
     PeEnEo
    0.55
    Star
    0.53
     *:
    0.52
    stars
    0.52
    *]
    0.51
    Act Density 0.216%

    No Known Activations