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

    Neuronpedia

    INDEX
    Explanations

    references to newness or innovation

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

    new something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.72
    UserScript
    -0.63
     BrowserModule
    -0.56
     חיצוניים
    -0.56
     AssemblyCulture
    -0.55
    Personendaten
    -0.54
    ьажоргаш
    -0.50
    IsPostBack
    -0.50
    __*/
    -0.49
     StatelessWidget
    -0.47
    POSITIVE LOGITS
    Layout
    0.42
     other
    0.41
     popoli
    0.40
    MoveNext
    0.40
     another
    0.39
     metais
    0.39
    subpackage
    0.39
     empire
    0.38
    peak
    0.38
    pole
    0.37
    Act Density 0.017%

    No Known Activations