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

    Neuronpedia

    INDEX
    Explanations

    get, obtain, retrieve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stwor
    0.44
     createFile
    0.42
    潁
    0.39
    newList
    0.38
     newList
    0.37
    AddRange
    0.37
    তায়
    0.37
    alphas
    0.37
     berangkat
    0.36
    मील
    0.36
    POSITIVE LOGITS
    获取
    1.23
     获取
    1.16
     obtaining
    1.07
     obtain
    1.05
     obtains
    1.05
    获得
    1.03
    を取得
    1.02
     الحصول
    1.01
    取得
    1.00
     retrieving
    0.96
    Act Density 0.079%

    No Known Activations