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

    Neuronpedia

    INDEX
    Explanations

    combining elements or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    カテゴ
    0.47
    onu
    0.45
     нагрузки
    0.44
     craz
    0.43
    pessoas
    0.43
    极端
    0.42
    ில்லியன்
    0.40
    हेलो
    0.40
    czych
    0.40
    ક
    0.40
    POSITIVE LOGITS
    ،
    0.55
     doesn
    0.52
     combines
    0.49
     lässt
    0.48
    。
    0.48
     Doesn
    0.48
     ließ
    0.45
    ，
    0.45
    、
    0.45
     combining
    0.44
    Act Density 0.003%

    No Known Activations