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

    Neuronpedia

    INDEX
    Explanations

    keywords:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ূর্ন
    0.39
    QV
    0.37
    Cru
    0.36
    waitForIdleSync
    0.35
    籽
    0.35
    滿
    0.34
     trưng
    0.34
    Emer
    0.34
    Clusters
    0.34
     कस्बे
    0.34
    POSITIVE LOGITS
    :
    0.46
    :-
    0.40
     audit
    0.40
     réfé
    0.39
    ：
    0.39
     குடி
    0.39
    bankruptcy
    0.39
    itoria
    0.38
     Audit
    0.37
     audits
    0.37
    Act Density 0.002%

    No Known Activations