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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods

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

    names starting with "St."

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.73
     ModelExpression
    -0.62
    tagHelperRunner
    -0.62
     desmotivaciones
    -0.62
    berdayakan
    -0.59
     Bucure
    -0.58
    esterno
    -0.58
    PerformLayout
    -0.57
    droje
    -0.56
     disambiguazione
    -0.56
    POSITIVE LOGITS
     St
    0.75
     Saint
    0.72
    St
    0.63
    Saint
    0.60
     ST
    0.57
     SAINT
    0.56
    Sta
    0.54
     Ste
    0.54
     Sta
    0.54
     State
    0.53
    Act Density 0.004%

    No Known Activations