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

    Neuronpedia

    INDEX
    Explanations

    career paths and future roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     skillset
    0.46
    スキル
    0.43
    講座
    0.39
    érm
    0.39
     keterampilan
    0.38
     सेकेंड
    0.38
     सेकंड
    0.37
    人々
    0.37
     emberek
    0.37
     muškar
    0.37
    POSITIVE LOGITS
     либо
    0.49
    திர
    0.48
     অথবা
    0.47
     अथवा
    0.45
    都能
    0.43
     또는
    0.43
     futura
    0.42
     Oregon
    0.41
    either
    0.41
     become
    0.41
    Act Density 0.035%

    No Known Activations