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

    Neuronpedia

    INDEX
    Explanations

    Dart, quantization, tensors, intelligence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.44
    스는
    0.41
    onya
    0.40
    มา
    0.39
    剂
    0.38
    筛选
    0.37
    ုံး
    0.37
    ol
    0.36
    算法
    0.36
    称为
    0.36
    POSITIVE LOGITS
     eğer
    0.44
     যেহেতু
    0.41
     propias
    0.38
     unimagin
    0.38
     televiz
    0.38
     disfruta
    0.37
     alguma
    0.37
     pozitiv
    0.36
     putem
    0.36
     propria
    0.36
    Act Density 0.134%

    No Known Activations