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

    Neuronpedia

    INDEX
    Explanations

    padding and margins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    न्होंने
    0.41
     član
    0.37
     হুমকির
    0.37
     AGRE
    0.36
     Myself
    0.36
     genom
    0.35
    knak
    0.35
    ▀
    0.35
     Appetite
    0.35
    andidate
    0.34
    POSITIVE LOGITS
     spacing
    0.53
     margins
    0.51
     Після
    0.47
     seconds
    0.46
    seconds
    0.45
    Seconds
    0.45
    margins
    0.44
    bigskip
    0.44
     between
    0.44
     distance
    0.43
    Act Density 0.027%

    No Known Activations