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

    Neuronpedia

    INDEX
    Explanations

    variable declarations in code

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

    variable declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nubes
    -0.32
     devons
    -0.29
     islas
    -0.29
     jiwa
    -0.29
     kuin
    -0.29
     garantía
    -0.29
     frankly
    -0.28
    Sede
    -0.28
     geral
    -0.28
     cielo
    -0.28
    POSITIVE LOGITS
    出版年
    1.09
     kasarigan
    1.03
    ########.
    0.98
     informée
    0.94
    Personendaten
    0.89
    parsedMessage
    0.80
     ब्रेकडाउन
    0.78
    tagHelperRunner
    0.78
    脚注の使い方
    0.74
     CreateTagHelper
    0.73
    Act Density 0.002%

    No Known Activations