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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     former
    -0.07
     harness
    -0.07
     корп
    -0.07
     maximum
    -0.07
     Constit
    -0.06
     cross
    -0.06
    _screen
    -0.06
     ramp
    -0.06
     Note
    -0.06
     NOTE
    -0.06
    POSITIVE LOGITS
    ＼＼
    0.08
     LayoutInflater
    0.07
    धर
    0.07
    _coupon
    0.07
     eldre
    0.07
     :＼
    0.07
     TreeSet
    0.07
    (mx
    0.06
    }&
    0.06
     vyk
    0.06
    Act Density 0.013%

    No Known Activations