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

    Neuronpedia

    INDEX
    Explanations

    rate of change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arose
    0.36
     arisen
    0.36
    स्टम
    0.35
     širo
    0.35
     Mapper
    0.35
    诞生
    0.34
     flipped
    0.34
     SDK
    0.34
     refreshed
    0.34
    ította
    0.34
    POSITIVE LOGITS
    随着
    0.89
     rapidly
    0.88
     steadily
    0.87
     slowly
    0.86
    隨著
    0.84
     lentamente
    0.82
     gradually
    0.79
     Slowly
    0.77
     exponentially
    0.75
     धीरे
    0.75
    Act Density 0.049%

    No Known Activations