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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     patron
    -0.07
     cela
    -0.07
    .Headers
    -0.06
    _la
    -0.06
    台
    -0.06
     fraudulent
    -0.06
    تب
    -0.06
     Jensen
    -0.06
    [top
    -0.06
     Brunswick
    -0.06
    POSITIVE LOGITS
     resembled
    0.08
    .ts
    0.07
    Coach
    0.07
    ‌پدیا
    0.07
    	constexpr
    0.07
    LL
    0.07
    Brush
    0.06
     엄
    0.06
     Forty
    0.06
    -under
    0.06
    Act Density 0.025%

    No Known Activations