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

    Neuronpedia

    INDEX
    Explanations

    specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     equality
    -0.06
     ك
    -0.06
    尝
    -0.06
     starving
    -0.06
    败
    -0.06
     kel
    -0.06
    ảy
    -0.06
    ốn
    -0.06
    嫂
    -0.06
     Sự
    -0.06
    POSITIVE LOGITS
    domain
    0.08
    .SetActive
    0.08
    $body
    0.08
    datagrid
    0.07
    cbd
    0.07
    _MODEL
    0.07
     Leban
    0.07
    ANDOM
    0.07
    _RAW
    0.07
    冰淇
    0.07
    Act Density 0.103%

    No Known Activations