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

    Neuronpedia

    INDEX
    Explanations

    other/others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    This
    0.55
    That
    0.54
    The
    0.52
    which
    0.45
    Thankfully
    0.45
    profession
    0.44
    Which
    0.44
    Pot
    0.43
    Ultimately
    0.42
    Therefore
    0.42
    POSITIVE LOGITS
     ఇతర
    0.48
     ሌሎች
    0.47
     інших
    0.47
     ಇತರ
    0.45
     sugiere
    0.43
     anderen
    0.42
     unconnected
    0.42
     ibang
    0.42
     других
    0.41
     অন্যান্য
    0.41
    Act Density 0.011%

    No Known Activations