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

    Neuronpedia

    INDEX
    Explanations

    names and naming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आंब
    0.40
     between
    0.38
     out
    0.38
     choking
    0.36
     शिक
    0.36
     zwischen
    0.36
     positive
    0.36
     यामध्ये
    0.36
    enin
    0.35
     berupa
    0.35
    POSITIVE LOGITS
     namesake
    1.15
     নামকরণ
    1.03
     eponymous
    0.93
    名字
    0.86
     이름
    0.86
     이름을
    0.85
     নামটি
    0.84
    名稱
    0.82
     નામ
    0.80
     name
    0.80
    Act Density 0.999%

    No Known Activations