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

    Neuronpedia

    INDEX
    Explanations

    Online purchases and downloads

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。
↵
    -0.07
    sville
    -0.07
     وه
    -0.07
    街
    -0.06
     terminate
    -0.06
    dfd
    -0.06
     ту
    -0.06
    _Tag
    -0.06
     lstm
    -0.06
     Trib
    -0.06
    POSITIVE LOGITS
    Declaration
    0.07
    (Language
    0.07
    BadRequest
    0.06
    ocr
    0.06
     Victor
    0.06
     기본
    0.06
     ]),↵
    0.06
     :.:
    0.06
     mädchen
    0.06
     důvodu
    0.06
    Act Density 0.112%

    No Known Activations