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

    Neuronpedia

    INDEX
    Explanations

    LI words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lush
    1.11
     liking
    1.09
     FIXME
    1.08
    另外
    1.07
    嶺
    1.07
     வழ
    1.05
    à
    1.04
     loạn
    1.04
    絊
    1.04
     Likewise
    1.04
    POSITIVE LOGITS
    icrous
    1.95
    kungan
    1.64
     Ipsum
    1.63
    chtenstein
    1.57
    rangian
    1.56
    utenants
    1.52
    coln
    1.51
    inescent
    1.49
     oln
    1.46
    ousine
    1.44
    Act Density 1.235%

    No Known Activations