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

    Neuronpedia

    INDEX
    Explanations

    marks and negative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -extra
    -0.08
     influencing
    -0.08
     Translate
    -0.08
    chrome
    -0.07
     Android
    -0.07
    $html
    -0.07
    bw
    -0.07
     Ninja
    -0.07
    html
    -0.07
     menus
    -0.07
    POSITIVE LOGITS
     penalties
    0.09
     पाकिस्तान
    0.09
     खिलाफ
    0.08
     rinc
    0.08
     arrib
    0.08
    处罚
    0.08
     rechaz
    0.08
     पंजाब
    0.08
     सकारात्मक
    0.08
     السل
    0.08
    Act Density 0.003%

    No Known Activations