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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and conditions associated with various academic, scientific, or statistical analyses

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

    lists or details following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     JAXBElement
    -0.48
    EDEFAULT
    -0.47
    cinnati
    -0.41
     Meksiku
    -0.40
     geschafft
    -0.40
     становника
    -0.38
    }{*}{}
    -0.38
     "..\..\..\
    -0.37
    Cyfeiriadau
    -0.37
    SuspendLayout
    -0.36
    POSITIVE LOGITS
    Hentet
    0.57
    CloseOperation
    0.51
    Datuak
    0.49
     <<<<<<<<<<<<<<
    0.48
     препратки
    0.42
    IsMutable
    0.41
    ModelSerializer
    0.39
    Độ
    0.38
    cuerdo
    0.36
    المناصب
    0.36
    Act Density 0.300%

    No Known Activations