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

    Neuronpedia

    INDEX
    Explanations

    looking at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᓴ
    0.41
    ৭
    0.39
    ("%
    0.39
     Juno
    0.38
    :=
    0.36
     sh
    0.36
    ارع
    0.36
     qued
    0.36
     Jupiter
    0.36
     Gemini
    0.35
    POSITIVE LOGITS
    Invite
    0.40
    ritical
    0.39
     المصفوفه
    0.39
     اج
    0.38
    Century
    0.38
    اؤ
    0.38
    Board
    0.38
    inghouse
    0.37
    Images
    0.37
    Convention
    0.37
    Act Density 0.000%

    No Known Activations