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

    Neuronpedia

    INDEX
    Explanations

    second or latter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     liturg
    0.61
     exorbit
    0.60
    ௭
    0.60
    ᕋ
    0.60
     демокра
    0.59
    󠁥
    0.58
    જરા
    0.57
    СТЕ
    0.57
     ー
    0.57
     NSFW
    0.56
    POSITIVE LOGITS
    Second
    0.75
     δεύτε
    0.71
    second
    0.70
    后者
    0.67
     второго
    0.66
    অন্যদিকে
    0.65
     второй
    0.64
     రెండో
    0.63
     seconda
    0.62
     вторая
    0.62
    Act Density 3.876%

    No Known Activations