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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Proc
    -0.06
    ridge
    -0.06
    一级
    -0.06
     Moz
    -0.06
     MANAGEMENT
    -0.06
    @[
    -0.06
     》
    -0.06
    IDGE
    -0.06
     QLatin
    -0.06
    ighest
    -0.06
    POSITIVE LOGITS
     showcased
    0.07
     能
    0.07
     tob
    0.07
     عرض
    0.07
     embar
    0.06
    osed
    0.06
    竞
    0.06
    ubectl
    0.06
    _up
    0.06
     endure
    0.06
    Act Density 0.027%

    No Known Activations