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

    Neuronpedia

    INDEX
    Explanations

    sets and elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ালার
    0.43
    Do
    0.40
    Start
    0.38
    Burn
    0.38
    巧克力
    0.38
    ...'
    0.38
    ...\
    0.37
    Gün
    0.37
    Gary
    0.37
    Base
    0.37
    POSITIVE LOGITS
    変更
    0.43
     نتی
    0.42
     Breton
    0.42
     आश्वासन
    0.41
     lähe
    0.41
     compounding
    0.41
    に関して
    0.41
     étudi
    0.40
     changing
    0.40
    몫
    0.40
    Act Density 0.000%

    No Known Activations