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

    Neuronpedia

    INDEX
    Explanations

    you can see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pertenece
    0.44
    名は
    0.43
     hierarch
    0.42
     nicht
    0.41
    et
    0.41
     grud
    0.41
     reluctance
    0.40
     hormon
    0.40
    いは
    0.40
    emiz
    0.40
    POSITIVE LOGITS
    чних
    0.41
    虎
    0.41
     thả
    0.40
     أد
    0.38
    و
    0.38
    HSI
    0.38
    辂
    0.38
    ᇁ
    0.38
     टिकट
    0.37
     当然
    0.37
    Act Density 0.001%

    No Known Activations