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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Deb
    -0.07
     Baseball
    -0.07
    eshire
    -0.07
    ock
    -0.07
     stimulate
    -0.06
     beautifully
    -0.06
     χρή
    -0.06
    Tuple
    -0.06
     Chambers
    -0.06
    cased
    -0.06
    POSITIVE LOGITS
    'nde
    0.07
     ГО
    0.06
    сор
    0.06
     єв
    0.06
    .urls
    0.06
     Ağustos
    0.06
    __));↵
    0.06
     shorts
    0.06
     JsonResponse
    0.06
     เจ
    0.06
    Act Density 0.003%

    No Known Activations