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

    Neuronpedia

    INDEX
    Explanations

    contributing to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    1.32
    ă
    1.16
    ı
    1.06
    बी
    0.93
    !\
    0.91
    äns
    0.90
    )।
    0.86
    ıları
    0.82
    ف
    0.81
    し
    0.81
    POSITIVE LOGITS
    i
    1.27
    u
    1.18
    z
    1.08
    n
    1.02
    in
    1.00
    at
    0.99
     contributions
    0.98
    al
    0.97
     contributors
    0.97
     contribution
    0.96
    Act Density 0.115%

    No Known Activations