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

    Neuronpedia

    INDEX
    Explanations

    AI-powered/based/enabled applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     của
    0.65
    eurs
    0.58
    ţa
    0.57
    iterator
    0.55
    ação
    0.55
     інші
    0.54
     براي
    0.54
    ﻮ
    0.53
    serde
    0.52
    olie
    0.52
    POSITIVE LOGITS
     them
    0.70
     merit
    0.55
     fervor
    0.55
    י
    0.54
     system
    0.54
     mistrust
    0.54
     mis
    0.53
     brain
    0.53
     Them
    0.53
    us
    0.53
    Act Density 0.361%

    No Known Activations