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

    Neuronpedia

    INDEX
    Explanations

    require

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kì
    -0.08
    BOSE
    -0.07
     OV
    -0.07
     установ
    -0.07
    ši
    -0.07
    цем
    -0.07
     частина
    -0.07
     películ
    -0.07
     tec
    -0.07
     الرو
    -0.06
    POSITIVE LOGITS
    :T
    0.06
     Removed
    0.06
    	email
    0.06
    \F
    0.06
    샵
    0.06
    Logout
    0.06
     format
    0.06
     }):
    0.06
    Permanent
    0.06
    !',↵
    0.06
    Act Density 0.000%

    No Known Activations