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

    Neuronpedia

    INDEX
    Explanations

    URLs and paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    selectTable
    0.41
    じめ
    0.40
    อังกฤษ
    0.40
     initio
    0.39
    holung
    0.39
     주제
    0.39
    țial
    0.38
     Hess
    0.38
     configuring
    0.38
     amply
    0.37
    POSITIVE LOGITS
    Abs
    0.45
    watch
    0.44
    pairs
    0.41
    网址
    0.41
     sigu
    0.40
    url
    0.40
    a
    0.40
    pool
    0.39
    Em
    0.38
    urls
    0.38
    Act Density 0.006%

    No Known Activations