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

    Neuronpedia

    INDEX
    Explanations

    scientific writing (articles)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fuck
    -0.08
    имв
    -0.06
    paramref
    -0.06
     pubb
    -0.06
     đ
    -0.06
    .dw
    -0.06
    ctest
    -0.06
     смог
    -0.06
    otence
    -0.06
    <<<<
    -0.06
    POSITIVE LOGITS
     //$
    0.07
     yaml
    0.06
    므로
    0.06
     vua
    0.06
    igration
    0.06
    /Subthreshold
    0.06
     NGC
    0.06
     Engineers
    0.06
     notorious
    0.06
     ),
↵
    0.06
    Act Density 0.327%

    No Known Activations