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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preserves
    -0.08
     украш
    -0.08
     சாத
    -0.08
    宴
    -0.08
     dishes
    -0.08
     дожд
    -0.08
    Jonathan
    -0.08
    .pre
    -0.07
     songs
    -0.07
     stylesheet
    -0.07
    POSITIVE LOGITS
     ಮೂರು
    0.11
     മൂന്ന്
    0.11
     három
    0.11
     pillars
    0.11
     üç
    0.11
     acronym
    0.11
     trei
    0.11
     നാല്
    0.11
     ત્રણ
    0.11
     Triple
    0.10
    Act Density 0.052%

    No Known Activations