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

    Neuronpedia

    INDEX
    Explanations

    but lately

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     উক্ত
    0.52
     এরূপ
    0.45
    上記
    0.45
     जिसमे
    0.45
     thereof
    0.44
     loosing
    0.40
     সাথে
    0.39
     implying
    0.39
     wobei
    0.39
     उपरोक्त
    0.39
    POSITIVE LOGITS
     —
    0.46
     nonprofit
    0.46
    近日
    0.45
     почти
    0.44
     quietly
    0.43
     ఇటీవల
    0.43
     बृहस्पतिवार
    0.43
    —
    0.42
     businesswoman
    0.41
     lately
    0.40
    Act Density 0.026%

    No Known Activations