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

    Neuronpedia

    INDEX
    Explanations

    categories of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    アクション
    0.47
    궪
    0.43
    within
    0.42
    小学
    0.42
    য়দ
    0.41
     이미
    0.41
    ாது
    0.40
    জা
    0.40
    лен
    0.40
    已经在
    0.40
    POSITIVE LOGITS
     seperti
    0.51
     like
    0.48
     جیس
    0.45
     zoals
    0.43
     hver
    0.43
     جیسا
    0.42
     dreams
    0.42
     مثل
    0.42
    ariously
    0.41
     مشابه
    0.41
    Act Density 0.002%

    No Known Activations