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

    Neuronpedia

    INDEX
    Explanations

    author

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bros
    -0.06
    (Pos
    -0.06
    ентов
    -0.06
     hwnd
    -0.06
    avan
    -0.06
     сол
    -0.06
    -Con
    -0.06
    bung
    -0.06
    uegos
    -0.06
    еты
    -0.06
    POSITIVE LOGITS
    震
    0.07
     nonetheless
    0.07
     nem
    0.07
     additionally
    0.07
    Copyright
    0.07
     fontFamily
    0.07
    usb
    0.06
     출장
    0.06
    (runtime
    0.06
     Aqu
    0.06
    Act Density 0.002%

    No Known Activations