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

    Neuronpedia

    INDEX
    Explanations

    plug.based onspace totracking *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    1.13
    （
    1.05
    /
    0.97
    (
    0.93
     "
    0.91
     seeking
    0.80
    或
    0.80
     ("
    0.79
     perceived
    0.78
     repeatedly
    0.77
    POSITIVE LOGITS
     เอ่อ
    1.20
     ähm
    1.04
     আমার
    1.02
    ？”
    1.02
     tenemos
    1.02
     нашей
    1.02
     наші
    1.01
     tonight
    1.00
     আমাদের
    0.99
     અમારા
    0.94
    Act Density 0.662%

    No Known Activations