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

    Neuronpedia

    INDEX
    Explanations

    i followed by action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝑛
    1.01
    на
    0.98
    𝑎
    0.90
    सूचना
    0.87
    ch
    0.86
    ֆ
    0.86
    ‌ای
    0.86
    k
    0.85
    ओं
    0.85
    𝘀
    0.83
    POSITIVE LOGITS
     Chaotic
    1.04
     unmet
    0.99
     nodig
    0.98
     Troubleshooting
    0.97
    జె
    0.97
    IContainer
    0.96
    куляр
    0.95
    MDE
    0.94
     Cited
    0.94
     ajud
    0.93
    Act Density 0.016%

    No Known Activations