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

    Neuronpedia

    INDEX
    Explanations

    describing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     demás
    1.58
    r
    1.47
    op
    1.46
    ó
    1.40
    š
    1.33
    uding
    1.32
    o
    1.28
    as
    1.27
    itics
    1.27
    jna
    1.26
    POSITIVE LOGITS
     दोघा
    1.06
     ensure
    1.01
    ע
    1.01
     woolen
    1.00
     impressive
    0.99
     impede
    0.99
    ላቸው
    0.99
     intravenous
    0.97
     each
    0.97
    ной
    0.97
    Act Density 0.050%

    No Known Activations