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

    Neuronpedia

    INDEX
    Explanations

    multi-lingual and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonché
    0.48
     assurent
    0.45
     inoltre
    0.44
    或者是
    0.44
     पनि
    0.43
     είναι
    0.43
    이지만
    0.43
     sowie
    0.42
    িসহ
    0.42
     కూడా
    0.42
    POSITIVE LOGITS
     અને
    0.78
     и
    0.73
     और
    0.72
     आणि
    0.71
    并
    0.69
     και
    0.64
     and
    0.63
     ਅਤੇ
    0.61
    และ
    0.58
    and
    0.57
    Act Density 0.179%

    No Known Activations