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

    Neuronpedia

    INDEX
    Explanations

    carriage return character `\r`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ン
    0.93
    ح
    0.90
    на
    0.79
     पड़े
    0.76
    ன்
    0.74
    н
    0.74
    ط
    0.73
    ी
    0.72
    ن
    0.72
    ू
    0.71
    POSITIVE LOGITS
    g
    0.71
        
    0.71
    Pokud
    0.65
     pokud
    0.64
     UX
    0.61
    ார்ப
    0.61
     Pyaar
    0.61
    П
    0.61
     GTEST
    0.60
    d
    0.60
    Act Density 0.005%

    No Known Activations