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

    Neuronpedia

    INDEX
    Explanations

    larger numbers and more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    萦
    0.40
    ρία
    0.40
    ্জন
    0.40
     constituting
    0.39
     speeding
    0.38
    лата
    0.38
     равна
    0.38
    deviceID
    0.38
     setiap
    0.38
     Fraction
    0.38
    POSITIVE LOGITS
     longer
    0.59
     بیشتری
    0.53
    継続
    0.51
    longer
    0.49
     훨씬
    0.48
     längre
    0.47
    更大的
    0.47
    もっと
    0.46
     extended
    0.46
    比較
    0.46
    Act Density 0.002%

    No Known Activations