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

    Neuronpedia

    INDEX
    Explanations

    import or code related

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ح
    1.10
    mm
    1.09
    wijk
    1.03
    ot
    1.02
    on
    1.00
     Rosetta
    1.00
    otin
    0.97
    km
    0.95
    mathspace
    0.94
    rand
    0.93
    POSITIVE LOGITS
    ッケージ
    1.17
    不过
    1.16
     الجهاز
    1.14
     dàng
    1.13
    ೀತ
    1.13
    慥
    1.13
    लिटी
    1.12
    也是
    1.10
     চিত্ত
    1.10
    JAVADOC
    1.09
    Act Density 0.002%

    No Known Activations