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

    Neuronpedia

    INDEX
    Explanations

    prime minister

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    1.02
    ↵↵
    0.91
    v
    0.90
    <
    0.89
    an
    0.86
    less
    0.84
    t
    0.83
    w
    0.83
    า
    0.80
     padrão
    0.79
    POSITIVE LOGITS
    प्रिल
    0.78
     RATE
    0.76
     lancement
    0.73
     exercices
    0.70
    影片
    0.70
    芑
    0.70
     LETTER
    0.69
     notizie
    0.68
     fortiter
    0.68
     augmente
    0.68
    Act Density 0.001%

    No Known Activations