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

    Neuronpedia

    INDEX
    Explanations

    fly-by-wire controls, contract, random, wheel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﮈ
    1.03
     marcó
    0.97
     oluşan
    0.95
    UIKit
    0.94
    ୬
    0.94
     ellos
    0.93
    ﮔ
    0.93
    ﮩ
    0.92
    पीएफ
    0.91
     повышения
    0.91
    POSITIVE LOGITS
    льним
    0.77
    ives
    0.71
    ic
    0.62
    س
    0.62
    ング
    0.61
    Colors
    0.61
    ח
    0.61
    ح
    0.59
    ज
    0.59
    亻
    0.58
    Act Density 0.001%

    No Known Activations