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

    Neuronpedia

    INDEX
    Explanations

    sitting as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     گرف
    -0.07
    ownik
    -0.07
    _YUV
    -0.07
     طل
    -0.06
     Kardash
    -0.06
     село
    -0.06
    テ
    -0.06
     avalanche
    -0.06
    ео
    -0.06
    ffd
    -0.06
    POSITIVE LOGITS
    ↵↵↵
    0.07
     intervening
    0.06
    ("?
    0.06
    .↵↵↵
    0.06
    нах
    0.06
    _%
    0.06
    очек
    0.06
     reports
    0.06
    Learning
    0.06
    ин
    0.06
    Act Density 0.006%

    No Known Activations