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

    Neuronpedia

    INDEX
    Explanations

    excessive or undesirable degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    larger
    1.09
    more
    1.02
    degree
    0.92
    faster
    0.92
    degrees
    0.91
    storms
    0.89
    splitext
    0.86
     नोटबुक
    0.84
     Rapids
    0.83
     degrees
    0.83
    POSITIVE LOGITS
    너무
    1.42
     much
    1.37
    Much
    1.26
     Much
    1.17
    ooo
    1.10
    过于
    1.09
    much
    1.08
     mnoho
    1.07
    oo
    1.04
    ン
    1.00
    Act Density 0.017%

    No Known Activations