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

    Neuronpedia

    INDEX
    Explanations

    this is because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     antiserum
    0.44
    ᅴ
    0.44
     একটি
    0.43
    មើ
    0.43
     caries
    0.43
    inheritDoc
    0.42
    aný
    0.42
     disparity
    0.42
     DEPEND
    0.42
     repatriation
    0.41
    POSITIVE LOGITS
    因为
    0.52
     क्योंकि
    0.49
     karena
    0.47
     perquè
    0.46
    เพราะ
    0.44
    क्योंकि
    0.43
     stesso
    0.42
     особенно
    0.42
     acompan
    0.42
     kerana
    0.41
    Act Density 0.065%

    No Known Activations