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

    Neuronpedia

    INDEX
    Explanations

    modern history and inventions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decaying
    0.83
     ہر
    0.79
     Каждый
    0.79
    Francis
    0.78
     каждый
    0.78
     گزر
    0.76
     каж
    0.74
     Occasionally
    0.74
     antigua
    0.73
     каждую
    0.71
    POSITIVE LOGITS
     modern
    1.55
     moderno
    1.53
     moderne
    1.43
     modernen
    1.40
     modernos
    1.39
     moderna
    1.32
    modern
    1.27
     modernas
    1.27
     современного
    1.25
     современных
    1.22
    Act Density 0.061%

    No Known Activations