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

    Neuronpedia

    INDEX
    Explanations

    unsigned long integers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Id
    0.51
    с
    0.46
     But
    0.44
    𝚃
    0.44
    dress
    0.44
    entityManager
    0.43
    Dress
    0.42
     ஸ்ட
    0.42
    But
    0.41
    𝚂
    0.40
    POSITIVE LOGITS
    最多的
    0.44
     occupied
    0.42
     draining
    0.41
     tä
    0.40
     translations
    0.39
    লাষ
    0.39
     pyroph
    0.39
     filings
    0.39
     drains
    0.39
     invoices
    0.39
    Act Density 0.000%

    No Known Activations