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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     berk
    -0.07
     Hit
    -0.07
    /sites
    -0.07
    悦
    -0.07
     Week
    -0.07
     Nancy
    -0.06
     Sexy
    -0.06
    坠
    -0.06
     ya
    -0.06
    是一种
    -0.06
    POSITIVE LOGITS
    �습니다
    0.07
    杜
    0.07
    ,$_
    0.07
    콜
    0.07
    ]+=
    0.07
    旅程
    0.07
     contour
    0.07
    턴
    0.07
    הור
    0.07
    	continue
    0.06
    Act Density 0.050%

    No Known Activations