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

    Neuronpedia

    INDEX
    Explanations

    Xe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     separat
    1.08
     ACM
    0.97
    ﺓ
    0.96
     MNR
    0.96
     ACLU
    0.95
     DMA
    0.94
     LWR
    0.94
     ERC
    0.93
     AMA
    0.93
     Cavaliers
    0.92
    POSITIVE LOGITS
    ف
    1.20
    ри
    0.96
    ди
    0.95
    т
    0.89
    ран
    0.87
    де
    0.86
    ट
    0.85
    بر
    0.84
    té
    0.84
    ری
    0.83
    Act Density 0.000%

    No Known Activations