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

    Neuronpedia

    INDEX
    Explanations

    conjunctions after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plays
    0.55
     hanging
    0.52
     sebagainya
    0.50
     march
    0.47
     потім
    0.42
    ?,?,
    0.41
     explored
    0.40
    othelium
    0.40
     др
    0.39
    സർ
    0.39
    POSITIVE LOGITS
     आणि
    2.09
     અને
    1.97
     এবং
    1.90
     and
    1.87
     और
    1.82
     ਅਤੇ
    1.81
     và
    1.80
     и
    1.77
     และ
    1.69
     και
    1.66
    Act Density 0.498%

    No Known Activations