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

    Neuronpedia

    INDEX
    Explanations

    whitespace characters, indicating a focus on formatting or structure in text

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

    structural markers in structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __":
    -0.54
    Personendaten
    -0.52
     ligiloj
    -0.52
    uxxxx
    -0.52
    yarnpkg
    -0.52
    IntoConstraints
    -0.52
    Hozzáférés
    -0.49
    DockStyle
    -0.47
     fédé
    -0.47
    Lähteet
    -0.44
    POSITIVE LOGITS
    ​
    1.36
    ​,
    0.97
    ​​
    0.95
     ​
    0.94
    )​
    0.88
    :​
    0.87
    ​​​
    0.87
    .​
    0.86
    ​.
    0.86
    ,​
    0.84
    Act Density 0.015%

    No Known Activations