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

    Neuronpedia

    INDEX
    Explanations

    novel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    الف
    -0.09
    الم
    -0.09
     بالم
    -0.08
     Ш
    -0.07
     bisc
    -0.07
     Atmos
    -0.07
    -mile
    -0.07
    restaurants
    -0.07
    생
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     ניתן
    0.07
     Dissertation
    0.07
    といって
    0.07
    iya
    0.07
    𝓒
    0.07
    .PictureBox
    0.07
     dúvida
    0.07
    .Dock
    0.07
    的独特
    0.07
     License
    0.07
    Act Density 0.002%

    No Known Activations