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

    Neuronpedia

    INDEX
    Explanations

    Javier Velázquez

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ános
    -0.79
    Spawn
    -0.76
    Moh
    -0.76
     BEHAVIOR
    -0.70
    LEC
    -0.69
     MICHIGAN
    -0.69
    esp
    -0.69
    ruf
    -0.69
    setOpaque
    -0.69
     geçmiş
    -0.68
    POSITIVE LOGITS
    ācija
    0.92
     visible
    0.84
     options
    0.79
    ()',
    0.78
     patent
    0.76
     długo
    0.76
    patent
    0.76
    花板
    0.75
    "]),
    0.75
    суль
    0.75
    Act Density 0.005%

    No Known Activations