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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seasonal
    -0.10
    ourses
    -0.08
     Seasonal
    -0.08
     utility
    -0.07
    utility
    -0.07
    (Post
    -0.07
     publication
    -0.07
    集合
    -0.07
    论文
    -0.07
    文
    -0.07
    POSITIVE LOGITS
     sırasında
    0.09
    .elapsed
    0.08
     Inser
    0.08
     సమయంలో
    0.08
     στιγμή
    0.08
     جهاز
    0.08
    	anim
    0.08
     gefert
    0.08
     lach
    0.08
     pne
    0.08
    Act Density 0.006%

    No Known Activations