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

    Neuronpedia

    INDEX
    Explanations

    start of alphabetic sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nke
    1.08
     entró
    0.98
     évek
    0.96
     Cid
    0.93
    었다
    0.91
    শ্বরের
    0.90
    hemeral
    0.90
     следующие
    0.90
    "@
    0.90
     Amerikaanse
    0.89
    POSITIVE LOGITS
    ，
    0.68
    عى
    0.66
     resolution
    0.65
    ارت
    0.64
     Cache
    0.64
    Chars
    0.64
     به
    0.63
    iers
    0.63
    ،
    0.62
    ants
    0.61
    Act Density 0.000%

    No Known Activations