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

    Neuronpedia

    INDEX
    Explanations

    without its

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    0.99
    ন
    0.97
    ਈ
    0.83
    ти
    0.82
    Ꮸ
    0.80
    ка
    0.78
    ատ
    0.76
    urilor
    0.76
    n
    0.75
    ン
    0.74
    POSITIVE LOGITS
    AutoGen
    0.95
    Issledovatel
    0.94
     сайте
    0.86
    䢙
    0.83
     Gita
    0.82
    bserv
    0.82
     konsumen
    0.82
     Tb
    0.80
     Trabajo
    0.79
     Choud
    0.79
    Act Density 0.001%

    No Known Activations