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

    Neuronpedia

    INDEX
    Explanations

    Descriptive writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cel
    -0.07
    004
    -0.07
     ihnen
    -0.07
     rebel
    -0.07
    .meta
    -0.07
     �
    -0.07
    �
    -0.06
     truthful
    -0.06
     queues
    -0.06
     scrap
    -0.06
    POSITIVE LOGITS
     Trom
    0.07
    .configureTestingModule
    0.07
     ชนะ
    0.07
     бур
    0.06
     Purdue
    0.06
    ậc
    0.06
    ों
    0.06
     Ultra
    0.06
    牌
    0.06
     ÜNİ
    0.06
    Act Density 0.002%

    No Known Activations