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

    Neuronpedia

    INDEX
    Explanations

    means that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     y
    -0.08
    GLE
    -0.07
     Resolution
    -0.07
    campo
    -0.07
    observer
    -0.07
     Download
    -0.06
     За
    -0.06
     زوج
    -0.06
     DISABLE
    -0.06
     distribution
    -0.06
    POSITIVE LOGITS
    reminder
    0.06
     nemá
    0.06
     acos
    0.06
    ottesville
    0.05
    .lib
    0.05
     견
    0.05
    bí
    0.05
    !!!
    0.05
     stew
    0.05
     Holidays
    0.05
    Act Density 0.022%

    No Known Activations