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

    Neuronpedia

    INDEX
    Explanations

    academic and research-related terminology and phrases

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

    our approach or method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.68
     propOrder
    -0.66
    richTextPanel
    -0.65
    featureID
    -0.61
     OFDb
    -0.59
    KommentareTeilen
    -0.58
    Personensuche
    -0.56
    bolista
    -0.54
     purpoſe
    -0.54
    Hochspringen
    -0.54
    POSITIVE LOGITS
     elektry
    0.36
     Swartz
    0.33
     Heilig
    0.31
    posób
    0.30
    reszcie
    0.30
     będę
    0.30
     włas
    0.30
    ggak
    0.29
     dasarnya
    0.29
    ContentLoaded
    0.29
    Act Density 0.220%

    No Known Activations