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

    Neuronpedia

    INDEX
    Explanations

    specific noun phrase after preposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     또는
    0.49
    approximately
    0.46
     approx
    0.46
     desired
    0.44
    例如
    0.44
     approximately
    0.43
     implies
    0.42
     approximate
    0.42
     Example
    0.41
    または
    0.40
    POSITIVE LOGITS
     hadn
    0.54
     새로
    0.52
     rumored
    0.50
    Coastal
    0.48
     החד
    0.48
     habíamos
    0.48
     rumoured
    0.47
     habían
    0.46
     wildflowers
    0.45
     había
    0.45
    Act Density 0.130%

    No Known Activations