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

    Neuronpedia

    INDEX
    Explanations

    specific numbers and their relationships in data or equations

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

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sagrado
    -0.41
     maravillosa
    -0.41
     expéri
    -0.40
     prachtige
    -0.40
     câmera
    -0.39
     Capacidad
    -0.39
    gæ
    -0.38
     dourado
    -0.38
     pioggia
    -0.37
     tiež
    -0.37
    POSITIVE LOGITS
    parsedMessage
    0.67
    endregion
    0.64
     mergeFrom
    0.63
     Italijani
    0.63
    tagHelperRunner
    0.60
    ||||||||
    0.60
     endregion
    0.60
     (_,
    0.60
    <unused27>
    0.58
    <unused48>
    0.58
    Act Density 0.075%

    No Known Activations