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

    Neuronpedia

    INDEX
    Explanations

    HOME to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ýv
    1.12
     xref
    1.09
    ОВА
    1.06
    Laws
    1.06
     ক্যাপ
    1.05
     Laws
    1.04
     uphe
    1.03
     sinister
    1.02
    Author
    1.01
     distortions
    1.00
    POSITIVE LOGITS
     fordi
    0.91
     though
    0.80
    просы
    0.80
    ade
    0.78
     संरक्षक
    0.78
     vel
    0.77
    がき
    0.76
     ile
    0.76
    atás
    0.74
     пожалуйста
    0.74
    Act Density 0.151%

    No Known Activations