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

    Neuronpedia

    INDEX
    Explanations

    sum of preceding numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    1.52
    .?
    1.29
    ؟.
    1.24
    ?.
    1.22
     though
    1.21
    :.
    1.19
     however
    1.18
     کی۔
    1.17
    。
    1.16
    ?
    1.14
    POSITIVE LOGITS
     (_,
    1.33
     드러
    1.28
    ंखला
    1.27
     공식
    1.26
     Παν
    1.26
     최종
    1.26
    '_
    1.21
     인도
    1.20
    ㄞ
    1.19
    브
    1.18
    Act Density 0.035%

    No Known Activations