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

    Neuronpedia

    INDEX
    Explanations

    http status codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    1.25
    h
    1.17
    iz
    1.14
    ü
    1.13
    al
    1.13
    p
    1.04
    是
    1.03
    m
    1.02
    ns
    1.00
    ло
    0.99
    POSITIVE LOGITS
    ’
    1.31
    ون
    1.25
    )’
    1.23
    िफिकेट
    1.21
    ין
    1.19
    ک
    1.16
    ي
    1.16
    ている
    1.10
    ’),
    1.09
    リ
    1.09
    Act Density 0.000%

    No Known Activations