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

    Neuronpedia

    INDEX
    Explanations

    losing/lost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TMZ
    -0.07
    赭
    -0.07
     tekn
    -0.07
    煨
    -0.07
    乂
    -0.07
     ogł
    -0.07
    Accent
    -0.07
    Ok
    -0.07
    (photo
    -0.06
    Tonight
    -0.06
    POSITIVE LOGITS
     Raum
    0.07
    דות
    0.06
    药
    0.06
     ]↵
    0.06
    รวจ
    0.06
    重要
    0.06
     cheeses
    0.06
    坽
    0.06
    而在
    0.06
    فص
    0.06
    Act Density 0.066%

    No Known Activations