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

    Neuronpedia

    INDEX
    Explanations

    say "|"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تصوير
    -0.08
     Fairy
    -0.08
    才发现
    -0.07
     anecd
    -0.07
     sugar
    -0.07
    失眠
    -0.07
     Snake
    -0.07
     ViewChild
    -0.07
    白色
    -0.07
     파일
    -0.07
    POSITIVE LOGITS
    تم
    0.08
    גע
    0.07
     gr
    0.07
    bles
    0.07
    据
    0.06
     mitigate
    0.06
    离
    0.06
    ודי
    0.06
     Dzi
    0.06
    ể
    0.06
    Act Density 0.001%

    No Known Activations