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

    Neuronpedia

    INDEX
    Explanations

    repeated patterns or structures, particularly in code or data formats

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

    code or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -1.09
    libft
    -0.93
    ChildScrollView
    -0.78
    SharedDtor
    -0.69
    IntoConstraints
    -0.65
    ITECH
    -0.61
    EndProject
    -0.59
    LookAnd
    -0.59
    KommentareTeilen
    -0.58
    ConstraintMaker
    -0.58
    POSITIVE LOGITS
     tone
    0.39
     conto
    0.38
     combined
    0.35
    addAction
    0.35
     def
    0.35
     Netto
    0.34
     thi
    0.34
     fermo
    0.34
     qua
    0.34
     consistent
    0.33
    Act Density 0.023%

    No Known Activations