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

    Neuronpedia

    INDEX
    Explanations

    function calls with arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </em>
    -1.28
    '
    -1.09
    结语
    -1.05
    ↵
    -1.05
    na
    -1.04
    是怎么回事
    -1.04
     bazen
    -1.02
    im
    -1.02
    examined
    -1.00
    ambassade
    -0.99
    POSITIVE LOGITS
    ꪖ
    1.34
    吅
    1.32
    懨
    1.28
     bolso
    1.27
    cú
    1.27
    tagHelper
    1.23
    ﱠ
    1.21
    をし
    1.20
    柰
    1.20
     bolí
    1.19
    Act Density 0.007%

    No Known Activations