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

    Neuronpedia

    INDEX
    Explanations

    help and shaping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RELATIVA
    0.61
     करेक्ट
    0.50
    вершен
    0.49
     cylinders
    0.48
     недостатки
    0.47
    части
    0.47
    brightness
    0.47
    tım
    0.46
     defects
    0.46
    министра
    0.46
    POSITIVE LOGITS
    va
    0.48
    estone
    0.47
    oder
    0.46
     প
    0.46
    isa
    0.46
    ↵
    0.44
     تا
    0.44
    ž
    0.44
     Response
    0.44
    س
    0.43
    Act Density 0.000%

    No Known Activations