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

    Neuronpedia

    INDEX
    Explanations

    stopwords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gay
    -0.07
    聚会
    -0.07
    ירוע
    -0.07
     EXTRA
    -0.07
     Blues
    -0.07
    普法
    -0.06
    荣誉称号
    -0.06
    tc
    -0.06
     Extract
    -0.06
     ак
    -0.06
    POSITIVE LOGITS
    绊
    0.08
    *self
    0.07
    #Region
    0.07
    RoutingModule
    0.07
    (',',$
    0.06
     fury
    0.06
    larg
    0.06
    _hooks
    0.06
    RIEND
    0.06
    ANDOM
    0.06
    Act Density 0.361%

    No Known Activations