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

    Neuronpedia

    INDEX
    Explanations

    conjunction and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    b
    0.42
    K
    0.38
    на
    0.38
     facilitates
    0.37
    f
    0.37
    ק
    0.36
    wk
    0.36
    and
    0.34
    ک
    0.34
     ਅਤੇ
    0.34
    POSITIVE LOGITS
    لي
    0.45
    ión
    0.38
    jší
    0.37
    จะ
    0.37
    ۔
    0.36
    你
    0.35
    ছে
    0.34
    ем
    0.34
     ឬ
    0.34
    ได้
    0.32
    Act Density 0.550%

    No Known Activations