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

    Neuronpedia

    INDEX
    Explanations

    email

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     анализ
    -0.07
    (src
    -0.07
    Agregar
    -0.07
    _comparison
    -0.06
    лів
    -0.06
    kenin
    -0.06
    (numero
    -0.06
    态
    -0.06
     Edit
    -0.06
    meniz
    -0.06
    POSITIVE LOGITS
    /page
    0.07
     summons
    0.06
     Tomáš
    0.06
     �
    0.06
     uninitialized
    0.06
     hotter
    0.06
    เตอร
    0.06
    Increased
    0.06
     settling
    0.06
     relocated
    0.06
    Act Density 0.013%

    No Known Activations