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

    Neuronpedia

    INDEX
    Explanations

    frequency adverbs and phrases indicating acknowledgment or affirmation

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

    describing states or consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bitField
    -0.46
     Felsen
    -0.43
    mell
    -0.42
     Comprom
    -0.42
     idiom
    -0.41
     comprom
    -0.41
    ICALS
    -0.41
     tromper
    -0.40
    kip
    -0.40
    vex
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.51
    تفصیلات
    0.49
    Erreferentziak
    0.43
    ImageContext
    0.43
    horabuena
    0.43
     StatelessWidget
    0.42
     hatta
    0.42
     ролях
    0.41
    CreateModel
    0.40
     Paglinawan
    0.40
    Act Density 0.036%

    No Known Activations