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

    Neuronpedia

    INDEX
    Explanations

    me and my

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gens
    0.78
    ES
    0.77
    pertension
    0.70
    mond
    0.70
    ギュア
    0.70
     enticing
    0.70
     tumult
    0.69
    非常有
    0.69
     Arrivals
    0.68
    Sal
    0.68
    POSITIVE LOGITS
     hago
    0.89
     считаю
    0.82
    吩
    0.78
    ഡ
    0.75
     decoupled
    0.75
     alang
    0.72
     除
    0.72
     robots
    0.72
    संस्करण
    0.71
    сут
    0.70
    Act Density 0.000%

    No Known Activations