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

    Neuronpedia

    INDEX
    Explanations

    among, along, including

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     which
    0.44
    pid
    0.41
    -
    0.41
     quickly
    0.39
     Dean
    0.39
     మాత్రం
    0.39
     마치
    0.38
     unap
    0.38
     instead
    0.37
     point
    0.37
    POSITIVE LOGITS
     многих
    0.51
    Among
    0.50
     многим
    0.50
     among
    0.48
     सहित
    0.48
     aswell
    0.47
    Along
    0.47
     Among
    0.46
     многие
    0.46
    Შ
    0.45
    Act Density 0.089%

    No Known Activations