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

    Neuronpedia

    INDEX
    Explanations

    pdf, document, template, guides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sculptural
    0.51
     sculptures
    0.49
     sculpture
    0.48
     selfies
    0.48
     resonators
    0.47
     pebbles
    0.47
     deodorant
    0.47
     televisions
    0.46
     sculpt
    0.46
     necklaces
    0.46
    POSITIVE LOGITS
     PDF
    1.45
    PDF
    1.37
    pdf
    1.32
     pdf
    1.27
    Pdf
    1.16
     PDFs
    1.14
     Pdf
    1.04
     পিডিএফ
    1.04
     पीडीएफ
    1.02
     документ
    0.85
    Act Density 0.268%

    No Known Activations