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

    Neuronpedia

    INDEX
    Explanations

    lists and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    1.03
    る
    1.03
    ا
    0.93
    त
    0.91
    деа
    0.91
    rógeno
    0.90
    ing
    0.90
     Thes
    0.87
    tır
    0.86
    ಿಂತ
    0.86
    POSITIVE LOGITS
    णिज्य
    0.92
     clamps
    0.85
     berjalan
    0.82
     reprises
    0.79
     compart
    0.79
    */
    0.78
    বৈশাখ
    0.78
    utsches
    0.78
    جے
    0.78
     notori
    0.77
    Act Density 0.040%

    No Known Activations