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

    Neuronpedia

    INDEX
    Explanations

    definitions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ട്ടു
    0.72
    们的
    0.70
    겸
    0.65
    Фу
    0.63
    Hobbies
    0.62
    Ри
    0.62
    围
    0.61
    Rf
    0.61
    们
    0.61
     Rash
    0.60
    POSITIVE LOGITS
     waarbij
    1.23
     অর্থাৎ
    1.16
     방식으로
    1.10
     yani
    1.07
     oppure
    1.06
     meaning
    1.04
     où
    1.02
     innebär
    1.02
     donde
    1.01
     یعنی
    1.01
    Act Density 0.488%

    No Known Activations