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

    Neuronpedia

    INDEX
    Explanations

    capable of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Авто
    0.43
     Caves
    0.42
     viktigt
    0.39
     Alert
    0.39
     बिल्कुल
    0.39
    uters
    0.39
     Raiders
    0.38
     максимум
    0.38
    ందా
    0.38
     Ranked
    0.38
    POSITIVE LOGITS
     indeed
    0.70
     actually
    0.64
    Indeed
    0.64
    actually
    0.63
     sizable
    0.60
    Actually
    0.57
    indeed
    0.57
     sizeable
    0.55
    事实上
    0.54
    实际上
    0.53
    Act Density 0.010%

    No Known Activations