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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    困难
    -0.09
     ઉભ
    -0.08
     મુશ્ક
    -0.08
    努力
    -0.08
     狠
    -0.08
     dificultades
    -0.08
     انگی
    -0.08
     berkembang
    -0.08
     лечения
    -0.08
     कठिन
    -0.08
    POSITIVE LOGITS
     whitespace
    0.08
     propriétaire
    0.07
     phishing
    0.07
     wła
    0.07
     proprietary
    0.07
    urent
    0.07
    Owner
    0.07
    �
    0.07
     confirmer
    0.07
     নয়
    0.07
    Act Density 0.022%

    No Known Activations