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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .chrome
    -0.06
     rico
    -0.06
     wings
    -0.06
     환경
    -0.06
    *out
    -0.06
    Executable
    -0.06
    ut
    -0.06
    改变
    -0.06
     constant
    -0.06
    High
    -0.06
    POSITIVE LOGITS
    ãeste
    0.07
    (StringUtils
    0.07
     CGAffineTransform
    0.07
    (',')[
    0.06
    .al
    0.06
    -trash
    0.06
    -rad
    0.06
    願い
    0.06
    ϊκ
    0.06
     Laz
    0.06
    Act Density 0.010%

    No Known Activations