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

    Neuronpedia

    INDEX
    Explanations

    infinite number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    栊
    0.42
    六年
    0.37
    竻
    0.36
    يش
    0.36
    மொ
    0.35
    iculum
    0.35
    нений
    0.35
     floribus
    0.35
    ⓗ
    0.35
     Lots
    0.35
    POSITIVE LOGITS
     infinitely
    0.91
     infinite
    0.83
     Infinite
    0.80
    Infinite
    0.75
     infin
    0.73
     infinit
    0.72
    INFIN
    0.72
     infinity
    0.71
    无限
    0.70
    ♾
    0.69
    Act Density 0.011%

    No Known Activations