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

    Neuronpedia

    INDEX
    Explanations

    square brackets and parentheses in the text

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

    list structures `[` or `[[`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.69
    extAlignment
    -0.65
     Wikimedijinoj
    -0.63
    Personensuche
    -0.60
     sostenibilidad
    -0.59
    ConstraintMaker
    -0.57
    expandindo
    -0.57
    ContentAsync
    -0.56
     Numerade
    -0.56
    EndContext
    -0.56
    POSITIVE LOGITS
    %[
    0.42
    [
    0.41
     [
    0.40
    []
    0.40
     me
    0.36
     cou
    0.35
     Fau
    0.35
     hos
    0.35
    [][]
    0.33
    []"
    0.31
    Act Density 0.002%

    No Known Activations