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

    Neuronpedia

    INDEX
    Explanations

    putting it together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    agos
    0.42
    Curt
    0.41
    kamp
    0.40
    nerg
    0.39
    aporan
    0.38
     conveyed
    0.38
    ätze
    0.38
    Clearly
    0.38
     جزء
    0.38
    itius
    0.37
    POSITIVE LOGITS
    好了
    0.41
    ী
    0.41
     よう
    0.38
     Philly
    0.38
     फाइनल
    0.37
    শেষে
    0.37
     gluon
    0.37
    বধূ
    0.37
     výsled
    0.37
    訖
    0.37
    Act Density 0.000%

    No Known Activations