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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    징
    -0.07
     JJ
    -0.06
     REL
    -0.06
    พ
    -0.06
    -player
    -0.06
     Went
    -0.06
    encers
    -0.06
     SOC
    -0.06
    ziehung
    -0.06
    Rel
    -0.06
    POSITIVE LOGITS
     );
↵
    0.08
    änd
    0.07
     опас
    0.06
     winner
    0.06
     //////////////////
    0.06
     Rather
    0.06
    غاز
    0.06
    ằm
    0.06
     während
    0.06
     ناب
    0.06
    Act Density 0.020%

    No Known Activations