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

    Neuronpedia

    INDEX
    Explanations

    URLs and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دوم
    0.21
     Soldaten
    0.21
     Ausgang
    0.20
     Böyle
    0.19
     walaupun
    0.19
    uparavant
    0.19
     Fernseh
    0.19
     erzählt
    0.18
     옛
    0.18
     paysans
    0.18
    POSITIVE LOGITS
    ড
    0.21
    WEBPACK
    0.20
    如何
    0.19
    이
    0.19
    ক
    0.19
    స్
    0.18
    스
    0.18
    异常
    0.18
    ম
    0.17
    ফ
    0.17
    Act Density 0.008%

    No Known Activations