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

    Neuronpedia

    INDEX
    Explanations

    needs of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لي
    0.52
    很大
    0.46
    лу
    0.46
    るので
    0.46
    类似于
    0.45
    تين
    0.45
    lara
    0.44
    nahme
    0.44
    يكل
    0.43
    مي
    0.43
    POSITIVE LOGITS
    या
    0.58
     kebutuhan
    0.56
     as
    0.54
     needs
    0.51
    ра
    0.50
    のみ
    0.50
    am
    0.49
    al
    0.49
     Needs
    0.48
    го
    0.48
    Act Density 0.023%

    No Known Activations