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

    Neuronpedia

    INDEX
    Explanations

    Technical documentation snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一点
    -0.09
    Архів
    -0.07
    phe
    -0.07
     corpse
    -0.06
    uddled
    -0.06
    比例
    -0.06
    _ISR
    -0.06
     sø
    -0.06
    と思う
    -0.06
    utility
    -0.06
    POSITIVE LOGITS
     KNOW
    0.07
    _PS
    0.07
    .Car
    0.07
    注意
    0.07
     Miche
    0.07
     Experienced
    0.07
    /New
    0.06
    stations
    0.06
     canned
    0.06
    (fb
    0.06
    Act Density 0.000%

    No Known Activations