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

    Neuronpedia

    INDEX
    Explanations

    4-letter words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    According
    0.28
    优化
    0.25
     Optimization
    0.24
     $(-
    0.24
     According
    0.23
    IGNORE
    0.23
    澫
    0.23
    LinkId
    0.22
    Utilization
    0.22
    |-|-
    0.22
    POSITIVE LOGITS
    ;,
    0.31
    ;',
    0.31
     supple
    0.30
     wears
    0.30
     זי
    0.29
     wore
    0.28
     cria
    0.27
     terrible
    0.27
     authorise
    0.27
     aute
    0.26
    Act Density 0.001%

    No Known Activations