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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "different."

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

    describing differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inerja
    -0.48
     pengend
    -0.46
     enggak
    -0.46
     pério
    -0.45
    merksamkeit
    -0.45
    ambién
    -0.45
     Funcion
    -0.44
    engesch
    -0.44
     matrícula
    -0.44
     hvil
    -0.43
    POSITIVE LOGITS
    parsedMessage
    0.56
    VersionUID
    0.56
    Portail
    0.49
    verifyException
    0.48
    Personensuche
    0.44
     betweenstory
    0.43
    steamcommunity
    0.43
    Архівовано
    0.43
     dAtA
    0.42
    MLLoader
    0.42
    Act Density 0.019%

    No Known Activations