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

    Neuronpedia

    INDEX
    Explanations

    makeup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adir
    -0.29
    akest
    -0.27
    estyle
    -0.26
    CanBe
    -0.26
    !.↵↵
    -0.25
     ..."↵↵
    -0.25
     inf
    -0.25
    .nd
    -0.24
    -prev
    -0.24
    à¸Ľà¸£à¸°à¹Ĥยà¸Ĭà¸Ļ
    -0.24
    POSITIVE LOGITS
     Ultimately
    0.25
    å¸ĤåľºéľĢæ±Ĥ
    0.24
     __("
    0.24
    unga
    0.23
     mirror
    0.23
    Intermediate
    0.23
    ç´¯
    0.23
     mirrors
    0.23
    çĻ»
    0.23
     worth
    0.23
    Act Density 2.403%

    No Known Activations