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

    Neuronpedia

    INDEX
    Explanations

    interactions and complexity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    는
    0.56
    দিনে
    0.54
    titleMargin
    0.53
    أة
    0.53
    "/>.
    0.52
    是我们
    0.52
     Diskussion
    0.52
     weiteren
    0.51
    $&
    0.51
     Weitere
    0.51
    POSITIVE LOGITS
    0.65
    hid
    0.61
    ot
    0.59
    ate
    0.59
    op
    0.59
     startups
    0.58
    ou
    0.58
     пато
    0.57
    hydroxy
    0.57
    ্যালে
    0.57
    Act Density 0.012%

    No Known Activations