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

    Neuronpedia

    INDEX
    Explanations

    elements related to fashion and style

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

    Rare or unusual words/tokens

    np_acts-logits-general · gemini-2.0-flash

    technical text, code, and scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.66
    ngrx
    -0.53
    calipsis
    -0.52
     générale
    -0.52
    WaitGroup
    -0.52
    enoord
    -0.52
     porcentual
    -0.51
    ωμα
    -0.51
     AssemblyCulture
    -0.51
    влению
    -0.51
    POSITIVE LOGITS
     Majefty
    0.65
     كومونز
    0.64
     للمعارف
    0.63
     ſeveral
    0.61
     reaſon
    0.60
     poffible
    0.58
     reafon
    0.56
    mero
    0.56
     juſt
    0.56
     perfons
    0.56
    Act Density 0.005%

    No Known Activations