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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     divert
    -0.07
    _HINT
    -0.06
     guarante
    -0.06
    unload
    -0.06
    *l
    -0.06
     jean
    -0.06
    агато
    -0.06
    овани
    -0.06
    iteur
    -0.06
     sıkıntı
    -0.06
    POSITIVE LOGITS
     PN
    0.06
    馆
    0.06
     beginners
    0.06
    $↵↵
    0.06
    ژه
    0.06
    (shape
    0.06
     initialization
    0.06
    SetText
    0.06
     Near
    0.06
     sua
    0.06
    Act Density 0.027%

    No Known Activations