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

    Neuronpedia

    INDEX
    Explanations

    character encoding or language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     МО
    0.49
    2
    0.47
     түр
    0.45
    หน้า
    0.44
    虜
    0.44
    ᙱ
    0.43
     வித்திய
    0.43
    変わ
    0.43
    ऱ
    0.42
    ний
    0.42
    POSITIVE LOGITS
     Cornish
    0.51
    养
    0.45
     gasoline
    0.44
     hydrocarbon
    0.42
     cơm
    0.42
     Confederate
    0.41
     君
    0.41
     Discounts
    0.41
     DF
    0.40
    redients
    0.40
    Act Density 0.001%

    No Known Activations