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

    Neuronpedia

    INDEX
    Explanations

    ordinary, extraordinary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blatant
    -0.07
    tems
    -0.07
     حم
    -0.07
     использу
    -0.06
    　l
    -0.06
     Vương
    -0.06
     민주
    -0.06
     ~(
    -0.06
     ◑
    -0.06
    似乎
    -0.06
    POSITIVE LOGITS
     extraordinary
    0.32
    ordinary
    0.17
     extraordinarily
    0.15
     extraordin
    0.11
     astonishing
    0.09
     surrendered
    0.08
    звичай
    0.08
     extravag
    0.07
     특별
    0.07
     extravagant
    0.07
    Act Density 0.003%

    No Known Activations