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

    Neuronpedia

    INDEX
    Explanations

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $=$
    1.38
    '
    1.32
     See
    1.28
     v
    1.25
    Cllr
    1.23
     unha
    1.19
    <h2>
    1.15
    ’
    1.15
    dated
    1.15
    sna
    1.14
    POSITIVE LOGITS
    rinsic
    3.43
     them
    3.39
     тебе
    3.38
    them
    3.36
     us
    3.26
    你了
    3.22
     THEM
    3.20
     fizik
    3.20
    伱
    3.13
     ngươi
    3.11
    Act Density 0.979%

    No Known Activations