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

    Neuronpedia

    INDEX
    Explanations

    "I'm" at start of text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ворот
    -0.08
    listar
    -0.08
     pills
    -0.08
     ответствен
    -0.08
     Decoder
    -0.07
     culp
    -0.07
    _math
    -0.07
     koul
    -0.07
     попрос
    -0.07
    ất
    -0.07
    POSITIVE LOGITS
     Wey
    0.08
    ृति
    0.08
    製
    0.07
     förs
    0.07
     carved
    0.07
     carve
    0.07
     periodic
    0.07
     releases
    0.07
    ेस
    0.07
     Outlook
    0.07
    Act Density 0.000%

    No Known Activations