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

    Neuronpedia

    INDEX
    Explanations

    comment symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Institutions
    -0.08
     Institution
    -0.08
     Kis
    -0.08
     Stiftung
    -0.08
     institutions
    -0.08
     Mosque
    -0.07
    эс
    -0.07
    әй
    -0.07
     enzyme
    -0.07
    ाउंड
    -0.07
    POSITIVE LOGITS
     برابر
    0.09
     yerine
    0.08
     poput
    0.08
    tru
    0.07
    ూ
    0.07
     gravit
    0.07
     whilst
    0.07
     ਦੀ
    0.07
     violates
    0.07
     vyr
    0.07
    Act Density 0.003%

    No Known Activations