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

    Neuronpedia

    INDEX
    Explanations

    discussions and themes related to race and representation

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

    other list many categories user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpose
    -0.49
     Kapit
    -0.44
    Purpose
    -0.43
    नीय
    -0.43
     kapture
    -0.42
     Corner
    -0.42
     olas
    -0.41
     Purpose
    -0.41
     PURPOSE
    -0.40
     trái
    -0.40
    POSITIVE LOGITS
     OFDb
    0.58
    verwijspagina
    0.56
     nahilalakip
    0.54
     للمعارف
    0.50
    MigrationBuilder
    0.50
    protoimpl
    0.46
    elemField
    0.46
    Vidite
    0.46
     للاسماء
    0.46
    estacks
    0.45
    Act Density 0.042%

    No Known Activations