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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to scientific findings and changes of state.

    oai_token-act-pair · gemini-2.0-flash

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.78
     EconPapers
    -0.75
     مرئيه
    -0.73
    )";
    -0.70
    Grüsse
    -0.69
    دانشنامهٔ
    -0.68
     Besøkt
    -0.65
    Égypte
    -0.65
     tartalomajánló
    -0.65
    -------------</
    -0.65
    POSITIVE LOGITS
    apimachinery
    0.39
    êt
    0.37
    Succ
    0.36
    لام
    0.36
    ソ
    0.35
     Suffer
    0.35
    미
    0.34
    waltung
    0.34
     near
    0.34
     Lamp
    0.34
    Act Density 1.975%

    No Known Activations