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

    Neuronpedia

    INDEX
    Explanations

    File extensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oblivious
    -0.08
    retrieve
    -0.08
    鲜明
    -0.07
    吸收
    -0.07
     Moody
    -0.07
    ENSE
    -0.06
     Khan
    -0.06
     scouts
    -0.06
     Bliss
    -0.06
    Ｋ
    -0.06
    POSITIVE LOGITS
    :Int
    0.07
    اجتماع
    0.07
    0.07
     popup
    0.07
     artyku
    0.07
    좌
    0.07
     stringByAppendingString
    0.07
    OwnProperty
    0.06
    强势
    0.06
    ugu
    0.06
    Act Density 0.002%

    No Known Activations