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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "definite."

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

    certainty or specificity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.89
     AssemblyCulture
    -0.84
    UserScript
    -0.75
     IBRARY
    -0.73
     Masyarakat
    -0.71
     kasarigan
    -0.71
    rungsseite
    -0.70
    ロウィン
    -0.70
     Photocase
    -0.69
    LabelTagHelper
    -0.69
    POSITIVE LOGITS
     definite
    1.73
    definite
    1.46
    inite
    0.96
     definitive
    0.83
     indefinite
    0.81
     definit
    0.74
     defin
    0.73
     Definitive
    0.73
     definida
    0.68
     défin
    0.67
    Act Density 0.006%

    No Known Activations