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

    Neuronpedia

    INDEX
    Explanations

    growth and rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وآ
    0.39
     ua
    0.38
    Proguard
    0.38
     SBS
    0.37
    おそらく
    0.37
     suffit
    0.37
     લા
    0.36
    سٹر
    0.36
    睽
    0.36
    ){}^
    0.36
    POSITIVE LOGITS
     progressively
    0.64
     accelerates
    0.62
     steadily
    0.57
     exponentially
    0.57
     slowly
    0.51
     illustrates
    0.50
     increases
    0.48
     grows
    0.47
    加速
    0.46
     gradually
    0.45
    Act Density 0.000%

    No Known Activations