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

    Neuronpedia

    INDEX
    Explanations

    Ace (1 or 11)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mux
    0.42
    dU
    0.40
    ौदा
    0.40
     ми
    0.39
    Cameras
    0.39
    Czas
    0.38
    ന്ധ
    0.37
     своими
    0.37
    йти
    0.37
    dL
    0.37
    POSITIVE LOGITS
     Ace
    0.79
     ace
    0.79
     ACE
    0.77
     aces
    0.71
    Ace
    0.70
     Aces
    0.69
    ACE
    0.61
    ace
    0.60
    エース
    0.55
     Aceh
    0.51
    Act Density 0.003%

    No Known Activations