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

    Neuronpedia

    INDEX
    Explanations

    are you able to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    2.13
    d
    1.72
    v
    1.70
    a
    1.59
    in
    1.56
    p
    1.55
    ed
    1.50
    et
    1.38
    on
    1.37
    em
    1.37
    POSITIVE LOGITS
    ط
    1.26
    り
    1.20
    го
    1.09
    ер
    1.05
    </h3>
    1.02
    த்தில்
    1.02
    عية
    0.98
    、“
    0.96
    </h5>
    0.95
    ту
    0.93
    Act Density 0.004%

    No Known Activations