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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     welcher
    -0.08
     Lotto
    -0.08
     Normal
    -0.08
     Carefully
    -0.08
     tento
    -0.07
     Berikut
    -0.07
     $("#"
    -0.07
     váš
    -0.07
     sesuai
    -0.07
     Tent
    -0.07
    POSITIVE LOGITS
     milhares
    0.09
     millions
    0.08
     outperform
    0.08
     millones
    0.08
     thousands
    0.08
     maneras
    0.08
    Thousands
    0.08
    jang
    0.08
     atyp
    0.07
     milliards
    0.07
    Act Density 0.073%

    No Known Activations