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

    Neuronpedia

    INDEX
    Explanations

    tokens following a period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tayyip
    0.50
     متاثر
    0.47
     kalangan
    0.47
    Couldn
    0.46
     সমূহ
    0.44
     Lohia
    0.44
    Well
    0.43
     MTV
    0.43
    ниципа
    0.43
    hitungan
    0.43
    POSITIVE LOGITS
    ój
    0.44
    ᒧ
    0.44
    ლი
    0.43
    灭
    0.43
     as
    0.42
    转
    0.42
     maail
    0.41
    形状
    0.41
    anny
    0.40
    绘制
    0.40
    Act Density 0.032%

    No Known Activations