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

    Neuronpedia

    INDEX
    Explanations

    Prevention Lifeline resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Goodreads
    0.71
    Gm
    0.68
     निमित
    0.68
    Detectable
    0.68
    段
    0.67
    第九
    0.66
    游戏
    0.65
     excuses
    0.64
     लेते
    0.64
     ninth
    0.64
    POSITIVE LOGITS
    ově
    0.54
     இருப்பினும்
    0.53
     care
    0.52
     বাড়
    0.52
    ье
    0.50
     Tutak
    0.49
    лк
    0.49
    bes
    0.48
    zag
    0.48
    ological
    0.47
    Act Density 0.124%

    No Known Activations