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

    Neuronpedia

    INDEX
    Explanations

    player actions and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    0.79
    i
    0.66
    ală
    0.62
    e
    0.61
    :
    0.61
    же
    0.59
    गंगा
    0.58
    *
    0.58
    overy
    0.57
    *}$
    0.57
    POSITIVE LOGITS
     was
    0.66
     participan
    0.49
     velocidades
    0.46
    ص
    0.46
    চ্চ
    0.46
     participates
    0.45
     erleben
    0.45
     has
    0.45
     consists
    0.45
     Player
    0.45
    Act Density 0.008%

    No Known Activations