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

    Neuronpedia

    INDEX
    Explanations

    LaTeX code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Encode
    -0.07
    ()",
    -0.07
    .Children
    -0.06
    Joe
    -0.06
     daytime
    -0.06
    \Action
    -0.06
     WebView
    -0.06
    .endswith
    -0.06
    Outputs
    -0.06
     Crazy
    -0.06
    POSITIVE LOGITS
    ặt
    0.07
    ्तक
    0.07
     nä
    0.07
     Ç
    0.06
     ebx
    0.06
     uç
    0.06
     depths
    0.06
    -long
    0.06
     resized
    0.06
    toc
    0.06
    Act Density 0.001%

    No Known Activations