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

    Neuronpedia

    INDEX
    Explanations

    listing entities and connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fortunately
    0.40
     وكذلك
    0.39
    だけでなく
    0.38
    以及
    0.37
     以及
    0.37
    부터
    0.36
    /∂
    0.36
    그리고
    0.35
     aż
    0.35
     až
    0.35
    POSITIVE LOGITS
     +
    0.49
    与
    0.49
    と
    0.47
     与
    0.45
     &
    0.44
    與
    0.43
    跟
    0.42
     x
    0.40
     იგი
    0.40
     與
    0.40
    Act Density 0.047%

    No Known Activations