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

    Neuronpedia

    INDEX
    Explanations

    topic headings and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     તેમજ
    0.31
     방법에
    0.28
     तसेच
    0.27
    だけでなく
    0.26
     छह
    0.25
    avgsalary
    0.25
     മാത്രമേ
    0.25
     sodass
    0.25
     වන
    0.24
     데이터를
    0.24
    POSITIVE LOGITS
    /
    0.40
     &
    0.33
    :
    0.32
     vs
    0.30
     /
    0.30
    ing
    0.29
     and
    0.29
    .
    0.28
     Importance
    0.28
    ism
    0.27
    Act Density 1.641%

    No Known Activations