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

    Neuronpedia

    INDEX
    Explanations

    amazing advertisement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ों
    1.12
    ные
    1.09
    ἲ
    1.05
     குறிப்பிட்ட
    1.05
    ⱪ
    1.04
    釟
    1.03
    짧
    1.02
    ким
    1.00
    கள்
    1.00
    чних
    0.99
    POSITIVE LOGITS
    .
    1.96
    t
    1.59
    c
    1.50
    f
    1.44
    r
    1.33
     .
    1.30
    in
    1.23
    m
    1.23
    การ
    1.22
    a
    1.19
    Act Density 0.064%

    No Known Activations