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

    Neuronpedia

    INDEX
    Explanations

    terms that signify totality or completeness

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

    entire, whole, full + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    -0.56
    EndContext
    -0.41
     celui
    -0.40
    การ
    -0.37
    ddots
    -0.36
    ///
    -0.36
    atorics
    -0.36
    katapos
    -0.35
     celle
    -0.35
    the
    -0.34
    POSITIVE LOGITS
    tvguidetime
    0.65
     Administrativna
    0.65
     Italijani
    0.58
     Taktlose
    0.53
    rungsseite
    0.53
     незавершена
    0.52
     nakalista
    0.52
    
    0.51
     vostra
    0.50
    IndentedString
    0.50
    Act Density 0.008%

    No Known Activations