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

    Neuronpedia

    INDEX
    Explanations

    24/7 available

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     हुए
    0.77
     received
    0.75
     אך
    0.73
    此前
    0.72
     backstage
    0.71
    來自
    0.71
     apud
    0.70
    ных
    0.70
     받은
    0.70
     recently
    0.69
    POSITIVE LOGITS
     EVERYTHING
    0.74
    uuuu
    0.70
    ที่จะ
    0.69
     सामान
    0.68
    に必要な
    0.68
    szyst
    0.66
    Everything
    0.66
    땜
    0.65
    Every
    0.64
     segala
    0.64
    Act Density 0.012%

    No Known Activations