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

    Neuronpedia

    INDEX
    Explanations

    windows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exhilarating
    -0.08
     Battlefield
    -0.08
     battlefield
    -0.07
     thrilling
    -0.07
     courageous
    -0.07
     diken
    -0.07
     bish
    -0.07
     tolerance
    -0.07
     перес
    -0.07
     Trusted
    -0.07
    POSITIVE LOGITS
     próprios
    0.09
     propios
    0.09
    亮
    0.09
     അപേക്ഷ
    0.08
     വീട
    0.08
     próprias
    0.08
    自己的
    0.08
     modernas
    0.08
     fenêtres
    0.08
    ിന്ദ
    0.08
    Act Density 0.015%

    No Known Activations