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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "first" in the text

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

    initial actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plazos
    -0.52
     ferons
    -0.44
    élimin
    -0.44
     élimin
    -0.44
     étoient
    -0.43
     costes
    -0.42
     mejoras
    -0.42
     Tasche
    -0.42
     enfans
    -0.41
     polaire
    -0.41
    POSITIVE LOGITS
    новь
    0.65
    malink
    0.64
    VersionUID
    0.64
    rogly
    0.60
    帖最后由
    0.59
    ISupport
    0.57
    دانشنامهٔ
    0.57
     initially
    0.57
    LabelTagHelper
    0.57
    OGND
    0.56
    Act Density 0.011%

    No Known Activations