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

    Neuronpedia

    INDEX
    Explanations

    feedback/awards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    922
    -0.07
     foolish
    -0.06
    261
    -0.06
    upt
    -0.06
    ادت
    -0.06
     slicing
    -0.06
    (milliseconds
    -0.06
    IFA
    -0.06
    :num
    -0.06
     grad
    -0.06
    POSITIVE LOGITS
    sequential
    0.07
    -tabs
    0.06
    -letter
    0.06
    érience
    0.06
    /favicon
    0.06
     Regards
    0.06
     안내
    0.06
     mdl
    0.06
     MenuItem
    0.06
     voj
    0.06
    Act Density 0.440%

    No Known Activations