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

    Neuronpedia

    INDEX
    Explanations

    description content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zm
    0.45
    дован
    0.44
    𝑧
    0.44
    zten
    0.43
    ใหญ่
    0.43
    бран
    0.43
    स्टम
    0.42
    перед
    0.41
     inade
    0.40
    oyen
    0.40
    POSITIVE LOGITS
     textual
    0.44
     punctuation
    0.44
     ጥላ
    0.44
     Marathi
    0.43
     infections
    0.41
     denunci
    0.40
     annotation
    0.40
     coatings
    0.40
     Sanskrit
    0.39
     freshen
    0.39
    Act Density 0.001%

    No Known Activations