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

    Neuronpedia

    INDEX
    Explanations

    Blaming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kHz
    -0.07
     luxurious
    -0.07
     universe
    -0.06
     knot
    -0.06
    Chair
    -0.06
     Damen
    -0.06
     pantry
    -0.06
     iframe
    -0.06
    (screen
    -0.06
     distrust
    -0.06
    POSITIVE LOGITS
     helf
    0.07
     справж
    0.07
     produ
    0.06
    ตล
    0.06
     condi
    0.06
     inflicted
    0.06
    대로
    0.06
     Пов
    0.06
    ucking
    0.06
    _COLORS
    0.06
    Act Density 0.013%

    No Known Activations