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

    Neuronpedia

    INDEX
    Explanations

    comparisons and quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Добав
    -0.07
    Add
    -0.07
    _KP
    -0.07
    ului
    -0.07
     mí
    -0.07
    ventus
    -0.07
    ้า
    -0.06
    Mo
    -0.06
    Related
    -0.06
    TR
    -0.06
    POSITIVE LOGITS
     Sak
    0.06
     rulings
    0.06
    олаг
    0.06
    luğ
    0.06
    flamm
    0.06
     эта
    0.06
     кож
    0.06
     establishing
    0.06
     작
    0.06
    _LINK
    0.05
    Act Density 0.128%

    No Known Activations