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

    Neuronpedia

    INDEX
    Explanations

    phrases related to challenges or difficulties, emphasizing their impact on experiences

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

    positive qualities and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.56
    AndEndTag
    -0.55
     שוליים
    -0.52
    OGND
    -0.45
     ModelExpression
    -0.44
     quedado
    -0.40
    懸命
    -0.39
    ɵɵ
    -0.39
     quede
    -0.38
    aktur
    -0.38
    POSITIVE LOGITS
     mystique
    0.45
    quels
    0.43
     sacred
    0.42
    WriteTagHelper
    0.42
    Sacred
    0.41
     Sacred
    0.40
    sacred
    0.40
     SUR
    0.40
     nakalista
    0.40
     recollections
    0.40
    Act Density 0.087%

    No Known Activations