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

    Neuronpedia

    INDEX
    Explanations

    difficult environments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pigments
    -0.08
     Aden
    -0.08
     Lav
    -0.08
    (lib
    -0.07
    summer
    -0.07
    ként
    -0.07
     towel
    -0.07
    Summer
    -0.07
     решили
    -0.07
    Lav
    -0.07
    POSITIVE LOGITS
     problemlos
    0.11
     പോലും
    0.11
    อนได้
    0.11
     sekal
    0.10
    에서도
    0.10
     alike
    0.10
     maupun
    0.09
     türlü
    0.09
     सहित
    0.09
     hinweg
    0.09
    Act Density 0.148%

    No Known Activations