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

    Neuronpedia

    INDEX
    Explanations

    ched

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    障
    -0.08
    陷
    -0.07
     risks
    -0.07
    更有
    -0.07
    洵
    -0.07
    瑕
    -0.06
    .cut
    -0.06
    uese
    -0.06
    �
    -0.06
    ToAdd
    -0.06
    POSITIVE LOGITS
    angular
    0.07
     버
    0.07
     Camera
    0.07
     Shen
    0.06
    叩
    0.06
    quantity
    0.06
    reopen
    0.06
     باسم
    0.06
    的安全
    0.06
     jig
    0.06
    Act Density 0.006%

    No Known Activations