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

    Neuronpedia

    INDEX
    Explanations

    generating new ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ק
    0.44
     ਅਤੇ
    0.43
    และ
    0.43
    와
    0.42
     совокуп
    0.42
     सुद्धा
    0.42
     साथ
    0.41
    랑
    0.41
    шки
    0.40
    รวม
    0.40
    POSITIVE LOGITS
     creates
    0.52
     pristine
    0.50
     ripples
    0.49
     undisturbed
    0.47
     generating
    0.46
     generates
    0.46
     new
    0.44
     creating
    0.43
     نئی
    0.43
     substrate
    0.43
    Act Density 0.015%

    No Known Activations