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

    Neuronpedia

    INDEX
    Explanations

    predictions, physical laws

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Й
    -0.07
     тра
    -0.07
     ада
    -0.07
    ]:↵
    -0.07
    JT
    -0.07
    ]['
    -0.07
     directions
    -0.06
    zam
    -0.06
     dialysis
    -0.06
     अक्ष
    -0.06
    POSITIVE LOGITS
    unteer
    0.09
     terbesar
    0.09
    wala
    0.09
    rede
    0.09
    আম
    0.08
     وعلى
    0.08
    avanaugh
    0.08
     يقع
    0.08
    িকার
    0.08
     الكبرى
    0.08
    Act Density 0.000%

    No Known Activations