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

    Neuronpedia

    INDEX
    Explanations

    installing and importing libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     _$_
    0.75
    청
    0.72
     सिरे
    0.69
    シミ
    0.67
     juist
    0.67
     الحي
    0.67
     يلي
    0.66
    NR
    0.66
    쳥
    0.65
    isit
    0.65
    POSITIVE LOGITS
     व्यायाम
    0.68
    ੇ
    0.66
     train
    0.64
    rainment
    0.63
    тин
    0.61
    डान
    0.60
     mb
    0.60
    Uma
    0.59
    mangle
    0.59
     shareholder
    0.59
    Act Density 0.006%

    No Known Activations