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

    Neuronpedia

    INDEX
    Explanations

    elements related to personal correspondence and communication etiquette

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

    read the rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nuages
    -0.35
    躇
    -0.33
     explicación
    -0.33
     plegable
    -0.31
    országban
    -0.31
     nuvem
    -0.30
    庁
    -0.30
    version
    -0.30
     garantías
    -0.30
     Explanation
    -0.29
    POSITIVE LOGITS
    NOPQRST
    0.70
     betweenstory
    0.65
    舺
    0.61
     препратки
    0.60
     propOrder
    0.60
    новниш
    0.59
    InputTagHelper
    0.56
    tagHelperRunner
    0.55
     personalised
    0.55
    endregion
    0.53
    Act Density 0.060%

    No Known Activations