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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity, comparisons, and generalizations

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

    "another," "single," "more," or "same."

    np_acts-logits-general · gemini-2.0-flash

    another, more, other, single

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     guías
    -0.54
     Wikiseite
    -0.51
     hué
    -0.49
     copias
    -0.49
     cerveja
    -0.49
     Comprometido
    -0.49
    berdayakan
    -0.49
     Abonnez
    -0.48
     templado
    -0.46
     ainfi
    -0.46
    POSITIVE LOGITS
    WireFormatLite
    0.64
    KommentareTeilen
    0.63
    eavour
    0.58
    URLException
    0.58
     Wab
    0.56
    OwnProperty
    0.55
    esez
    0.55
    vro
    0.54
    ElementException
    0.54
    fortawesome
    0.54
    Act Density 0.320%

    No Known Activations