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

    Neuronpedia

    INDEX
    Explanations

    syntactical constructs or code blocks in programming language syntax

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

    start of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }{*}{}
    -0.51
     gitara
    -0.47
    uario
    -0.47
     nieve
    -0.43
     Penga
    -0.43
    ładka
    -0.43
    DataPropertyName
    -0.42
    Sådan
    -0.42
    ientôt
    -0.42
     motocicletas
    -0.42
    POSITIVE LOGITS
    styleType
    0.58
    AddHtmlAttribute
    0.58
    verifyException
    0.54
    parsedMessage
    0.54
    WithIOException
    0.53
    implements
    0.51
    BeginInit
    0.48
    Espèce
    0.47
     CanadaChoose
    0.46
     mergeFrom
    0.45
    Act Density 0.004%

    No Known Activations