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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Msg
    -0.07
     pickle
    -0.07
     Bridge
    -0.07
    -li
    -0.06
     Than
    -0.06
     paralysis
    -0.06
     năm
    -0.06
    HTMLElement
    -0.06
     ties
    -0.06
     goo
    -0.06
    POSITIVE LOGITS
    اخر
    0.07
    ере
    0.06
     forging
    0.06
    endra
    0.06
    روط
    0.06
    -pressure
    0.06
    εργ
    0.06
     thủy
    0.06
    访问
    0.06
    ρίζ
    0.06
    Act Density 0.123%

    No Known Activations