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

    Neuronpedia

    INDEX
    Explanations

    i, j, k loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ꭴ
    0.48
    ेंगू
    0.47
    <unused28>
    0.46
    𒆷
    0.46
     ყველ
    0.46
    皁
    0.45
     élytres
    0.44
    Glen
    0.44
    omerang
    0.44
     Braunsch
    0.42
    POSITIVE LOGITS
     i
    0.80
    i
    0.60
     n
    0.56
     ith
    0.56
     j
    0.55
    j
    0.54
     ii
    0.53
     k
    0.52
     him
    0.51
    k
    0.50
    Act Density 0.059%

    No Known Activations