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

    Neuronpedia

    INDEX
    Explanations

    terms related to evaluation, capability, and performance attributes

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

    states and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.66
    outWeight
    -0.58
    mpagne
    -0.56
    rawDesc
    -0.54
    ArgsConstructor
    -0.52
    arangay
    -0.52
    protoimpl
    -0.51
    wiſe
    -0.50
    attutto
    -0.49
    GEBURTSDATUM
    -0.49
    POSITIVE LOGITS
     المعيارى
    0.38
    retudo
    0.38
     llamados
    0.29
    strijden
    0.29
     extranjero
    0.29
     extranjera
    0.28
     dispuestos
    0.28
     vérité
    0.28
     ejecutivo
    0.28
     Jesucristo
    0.28
    Act Density 0.488%

    No Known Activations