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

    Neuronpedia

    INDEX
    Explanations

    governance model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.77
     for
    1.07
    j
    1.03
    d
    1.02
    m
    0.99
    a
    0.90
    де
    0.88
    tä
    0.88
    RA
    0.84
     änd
    0.83
    POSITIVE LOGITS
    ও
    1.11
    ר
    1.09
    р
    1.08
    gover
    1.07
    ता
    1.02
     gouver
    1.00
     مرکز
    1.00
     ی
    0.99
    ур
    0.98
    も
    0.96
    Act Density 0.007%

    No Known Activations