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

    Neuronpedia

    INDEX
    Explanations

    there are or is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Took
    0.62
    ৃঙ্খ
    0.61
     பாதிக்கிறது
    0.61
    保持
    0.60
    具有
    0.58
    ⿴
    0.58
     করিনি
    0.57
     বললাম
    0.56
    Dont
    0.56
    获得了
    0.56
    POSITIVE LOGITS
     are
    1.42
     were
    1.23
    ’
    1.19
     aren
    1.12
    '
    1.12
     exists
    1.09
     aree
    1.03
     isn
    1.03
    FORE
    0.98
     ARE
    0.97
    Act Density 0.243%

    No Known Activations