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

    Neuronpedia

    INDEX
    Explanations

    diff outputs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    手臂
    -0.07
    男士
    -0.07
    翅膀
    -0.07
    镥
    -0.07
     teaspoon
    -0.07
    ஸ
    -0.07
     всё
    -0.07
    臂
    -0.07
     dozen
    -0.07
    bracht
    -0.07
    POSITIVE LOGITS
     хорошо
    0.08
    ↵    ↵    ↵
    0.07
        
↵
    0.07
     estruct
    0.07
    产地
    0.07
    .ecore
    0.06
    (long
    0.06
    -util
    0.06
     producción
    0.06
    """↵
    0.06
    Act Density 0.001%

    No Known Activations