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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases, categorizing concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    见
    0.38
    摘要
    0.36
    見
    0.36
    เห็น
    0.36
     الظ
    0.36
    得分
    0.35
    saw
    0.35
     வரவே
    0.34
     SOURCES
    0.34
     thấy
    0.34
    POSITIVE LOGITS
     correct
    0.43
    ျေး
    0.42
     piss
    0.42
    нен
    0.41
     lis
    0.41
     protects
    0.40
    anis
    0.39
     ether
    0.39
     filing
    0.38
    OLS
    0.38
    Act Density 0.000%

    No Known Activations