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

    Neuronpedia

    INDEX
    Explanations

    less

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (mask
    -0.08
    #!
    -0.07
    /@
    -0.07
    新增
    -0.07
     حق
    -0.07
    ();)
    -0.06
    唐朝
    -0.06
    جماع
    -0.06
    akış
    -0.06
    兼职
    -0.06
    POSITIVE LOGITS
    IRECTION
    0.08
    Bro
    0.07
     seine
    0.07
    lick
    0.07
     TRAN
    0.07
     Worce
    0.07
    wę
    0.07
    プレ
    0.07
    øy
    0.07
    führung
    0.07
    Act Density 0.001%

    No Known Activations