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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Beginning
    -0.08
     getList
    -0.07
     casually
    -0.06
     tim
    -0.06
     realize
    -0.06
     indication
    -0.06
     necess
    -0.06
    勤
    -0.06
     increases
    -0.06
    策
    -0.06
    POSITIVE LOGITS
     círk
    0.08
    ickname
    0.07
     duplicated
    0.06
     uydu
    0.06
    )?.
    0.06
    ULO
    0.06
    šk
    0.06
    ImplOptions
    0.06
    čer
    0.06
     vybav
    0.06
    Act Density 0.115%

    No Known Activations