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

    Neuronpedia

    INDEX
    Explanations

    headings and section markers indicating the structure of a document

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

    restorable, replaceable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setupUi
    -0.48
    <bos>
    -0.44
    Citiți
    -0.43
     enfin
    -0.41
     PyTuple
    -0.41
    docx
    -0.40
    VersionUID
    -0.40
    reszcie
    -0.39
    guisement
    -0.39
     épu
    -0.39
    POSITIVE LOGITS
    rungsseite
    0.52
     disambiguazione
    0.52
    0.51
     ſte
    0.42
     blin
    0.42
    PreExecute
    0.42
     raiſ
    0.41
     uſ
    0.41
     ſta
    0.40
    moid
    0.40
    Act Density 0.000%

    No Known Activations