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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _WE
    -0.08
    Brown
    -0.07
    �
    -0.07
    CJK
    -0.07
     Clown
    -0.07
     Brun
    -0.06
    епти
    -0.06
     двиг
    -0.06
    Disallow
    -0.06
    Gatt
    -0.06
    POSITIVE LOGITS
     nas
    0.16
     Nas
    0.12
     nasal
    0.12
     NAS
    0.12
    NAS
    0.09
    as
    0.08
    asal
    0.08
    ас
    0.07
    nas
    0.07
    새
    0.07
    Act Density 0.005%

    No Known Activations