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

    Neuronpedia

    INDEX
    Explanations

    protonated forms, protonation, proton pumps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    1.27
    u
    1.25
    ar
    1.20
    i
    1.09
    at
    1.08
    an
    1.08
    as
    1.06
    w
    0.99
    ay
    0.97
    io
    0.93
    POSITIVE LOGITS
     reasoned
    0.95
     beerCount
    0.95
    ㈢
    0.93
     أول
    0.92
    :
    0.92
    会
    0.91
    <
    0.91
     وأ
    0.90
    يكا
    0.88
     أب
    0.88
    Act Density 0.000%

    No Known Activations