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

    Neuronpedia

    INDEX
    Explanations

    structural elements or formatting in text

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

    mathematical and scientific notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.67
     ddelwed
    -0.65
    ロウィン
    -0.64
    SharedCtor
    -0.64
    citroën
    -0.63
    ValueGeneration
    -0.61
     müſſen
    -0.60
    ValueStyle
    -0.60
    ſelben
    -0.60
     HasFactory
    -0.59
    POSITIVE LOGITS
    malı
    0.31
     [
    0.28
    gefügt
    0.28
    oup
    0.27
    TableAdapter
    0.27
    surate
    0.26
     A
    0.26
    른
    0.25
     un
    0.25
    Արտաքին
    0.25
    Act Density 0.016%

    No Known Activations