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

    Neuronpedia

    INDEX
    Explanations

    cost per

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    0.99
    ك
    0.98
    да
    0.98
    ंद
    0.95
     slick
    0.95
    ER
    0.92
    िक
    0.89
    но
    0.88
     +
    0.86
    ande
    0.85
    POSITIVE LOGITS
    theoretic
    1.19
    choline
    1.14
     대해서
    1.10
    translational
    1.09
    ultimate
    1.09
     ಎಲ್ಲಾ
    1.06
    tutorials
    1.06
    这样一个
    1.04
    mlst
    1.04
     atores
    1.03
    Act Density 0.000%

    No Known Activations