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

    Neuronpedia

    INDEX
    Explanations

    lists of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     czyli
    0.45
    และการ
    0.38
    Economic
    0.37
     and
    0.36
    Arithmetic
    0.35
    ：
    0.34
    ↵
    0.34
    Ranking
    0.33
    ד
    0.33
    Governance
    0.33
    POSITIVE LOGITS
    ூரில்
    0.39
     ისინი
    0.39
     அனைத்து
    0.37
     endeav
    0.37
     Использу
    0.36
     ಯಾವುದೇ
    0.36
     स्वीकार
    0.35
     использует
    0.35
     உடலில்
    0.35
     utilisent
    0.35
    Act Density 0.153%

    No Known Activations