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

    Neuronpedia

    INDEX
    Explanations

    Sincerely, followed by name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IF
    0.32
    ствует
    0.32
    大约
    0.31
    UFF
    0.31
     বছরে
    0.31
     அதிசயங்கள்
    0.31
     sanity
    0.31
    URF
    0.31
     eases
    0.31
     ಶತ
    0.30
    POSITIVE LOGITS
    Nev
    0.34
    ↵
    0.33
    givings
    0.31
    ير
    0.31
    ,}
    0.31
    ھار
    0.31
    ❜
    0.30
    зов
    0.28
     tiro
    0.28
    gnię
    0.28
    Act Density 0.014%

    No Known Activations