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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Represents
    -0.07
    beros
    -0.07
    annah
    -0.07
    abel
    -0.07
     Osman
    -0.06
    σεων
    -0.06
    .UseFont
    -0.06
    imi
    -0.06
     comenz
    -0.06
    бов
    -0.06
    POSITIVE LOGITS
     sacrificing
    0.06
     Newspaper
    0.06
     USART
    0.06
     Respons
    0.06
     suffer
    0.06
     warnings
    0.06
     traders
    0.06
     trưởng
    0.06
    nos
    0.06
    DU
    0.06
    Act Density 0.000%

    No Known Activations