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

    Neuronpedia

    INDEX
    Explanations

    prime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     апр
    -0.07
     гро
    -0.07
     फर
    -0.07
     en
    -0.07
     переход
    -0.07
     pokud
    -0.06
    OUNDS
    -0.06
    합니다
    -0.06
    GHz
    -0.06
     більш
    -0.06
    POSITIVE LOGITS
     famously
    0.07
    LIKE
    0.06
    istration
    0.06
    えない
    0.06
     milestones
    0.06
    verty
    0.06
     Traff
    0.06
    дии
    0.06
    Tabs
    0.06
     [#
    0.06
    Act Density 0.014%

    No Known Activations