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

    Neuronpedia

    INDEX
    Explanations

    different instances of quoted speech or dialogue in the text

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

    start of quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.51
     parachoque
    -0.45
     autobuses
    -0.41
     vuelto
    -0.40
     complementos
    -0.40
     znamen
    -0.39
     Abschluss
    -0.39
     olvides
    -0.39
     Karriere
    -0.39
     embreagem
    -0.39
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.77
    ConstraintMaker
    0.65
    MigrationBuilder
    0.59
    SourceChecksum
    0.58
     متعلقه
    0.48
     للمعارف
    0.47
    endpush
    0.47
     كومونز
    0.43
    LookAnd
    0.43
     Photocase
    0.43
    Act Density 0.009%

    No Known Activations