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

    Neuronpedia

    INDEX
    Explanations

    software and technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    s
    -1.34
    t
    -1.18
    i
    -1.05
    er
    -1.05
    d
    -0.99
    ه
    -0.98
    n
    -0.97
    m
    -0.96
    e
    -0.91
    a
    -0.82
    POSITIVE LOGITS
     propOrder
    0.62
    +#+#
    0.53
     متعلقه
    0.52
     виправивши
    0.51
    Билгалдахарш
    0.51
    politico
    0.51
    IsContent
    0.50
    UpInside
    0.50
    RTLD
    0.49
    BeforeClass
    0.49
    Act Density 1.795%

    No Known Activations