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

    Neuronpedia

    INDEX
    Explanations

    run multiple

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Perf
    0.52
     Tum
    0.46
    0.44
    **
    0.43
    Trans
    0.42
    Ins
    0.42
    Bott
    0.41
    os
    0.41
    Loc
    0.41
     Tram
    0.41
    POSITIVE LOGITS
     ойнойт
    0.53
     实现
    0.51
     ойной
    0.49
     toDo
    0.49
     assistenza
    0.48
     অর্চনা
    0.48
    LOTREntity
    0.48
     JavaBeans
    0.48
    স্ট্র
    0.47
    㡱
    0.47
    Act Density 0.002%

    No Known Activations