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

    Neuronpedia

    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ченко
    -0.07
    orsi
    -0.06
     Boyle
    -0.06
    [row
    -0.06
    ously
    -0.06
    일
    -0.06
    _WARNING
    -0.06
     тверд
    -0.06
     HttpNotFound
    -0.06
    regor
    -0.06
    POSITIVE LOGITS
     study
    0.07
     ülkenin
    0.06
     çalışma
    0.06
     tartış
    0.06
     $_[
    0.06
     dbl
    0.06
     judgments
    0.06
     race
    0.06
     admir
    0.06
     anymore
    0.06
    Act Density 0.033%

    No Known Activations