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

    Neuronpedia

    INDEX
    Explanations

    file.py

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     murderous
    0.42
     مختصر
    0.38
     grumpy
    0.37
     بیاکت
    0.36
     ګرځ
    0.35
     conclusão
    0.34
     వ్యక్
    0.34
     دوسروں
    0.34
     بابەت
    0.33
     politič
    0.33
    POSITIVE LOGITS
     which
    0.50
    which
    0.46
     with
    0.44
     that
    0.44
     которая
    0.43
     for
    0.41
    that
    0.41
    с
    0.41
     которые
    0.41
     whose
    0.40
    Act Density 3.544%

    No Known Activations