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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .inline
    -0.08
     aldı
    -0.07
     Coordinates
    -0.07
     Programme
    -0.07
    لية
    -0.07
     dikk
    -0.07
    umé
    -0.07
    OLL
    -0.07
    -plane
    -0.07
     Daar
    -0.07
    POSITIVE LOGITS
     اخبار
    0.10
     injustice
    0.09
     scarcity
    0.09
     न्याय
    0.09
     notícias
    0.09
     inevit
    0.09
    ruptcy
    0.09
     vengeance
    0.09
     ನ್ಯಾಯ
    0.09
    失败
    0.09
    Act Density 0.021%

    No Known Activations