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

    Neuronpedia

    INDEX
    Explanations

    parsing markdown and code functionality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जरूर
    0.45
    Mord
    0.41
     MODKEY
    0.41
    В
    0.41
    INION
    0.40
    hear
    0.39
     जरुर
    0.39
    K
    0.39
     समुदाय
    0.39
    ค
    0.39
    POSITIVE LOGITS
    *;
    0.47
    䨋
    0.47
     *.
    0.42
     軍
    0.42
    軍
    0.41
    *.
    0.40
     quân
    0.40
    *',
    0.39
    ;(
    0.39
    ফটেন্যান্ট
    0.39
    Act Density 0.000%

    No Known Activations