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

    Neuronpedia

    INDEX
    Explanations

    specific products or services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    没有
    0.54
    有可能
    0.47
    不是
    0.45
    ra
    0.43
    當地
    0.43
    不够
    0.43
    不
    0.43
    不太
    0.41
    ক
    0.41
     مختلفة
    0.40
    POSITIVE LOGITS
     and
    0.65
     a
    0.59
     in
    0.49
     as
    0.43
     an
    0.42
    apping
    0.41
     {
    0.41
     at
    0.41
     with
    0.40
    i
    0.40
    Act Density 0.945%

    No Known Activations