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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    egra
    -0.06
     campground
    -0.06
    нок
    -0.06
    _None
    -0.06
    consts
    -0.06
     segu
    -0.06
     jer
    -0.06
     downloader
    -0.06
     Yep
    -0.06
     Thumb
    -0.06
    POSITIVE LOGITS
    sel
    0.07
    하지
    0.07
    attr
    0.06
     udrž
    0.06
     nitelik
    0.06
     mongoose
    0.06
    opy
    0.06
    [min
    0.06
    ξεις
    0.06
    によ
    0.06
    Act Density 0.006%

    No Known Activations