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

    Neuronpedia

    INDEX
    Explanations

    multilingual and non-english characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ூரில்
    0.47
     prophylactic
    0.47
    Esper
    0.44
    0.40
    v
    0.40
    0.39
    ({
    0.38
    ²/
    0.38
    тным
    0.38
    macros
    0.38
    POSITIVE LOGITS
     ্
    0.44
     يد
    0.43
    ଗ
    0.43
    囘
    0.43
     하나의
    0.41
     تد
    0.39
    owna
    0.39
    ất
    0.39
    䢙
    0.39
    擡
    0.39
    Act Density 0.000%

    No Known Activations