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

    Neuronpedia

    INDEX
    Explanations

    reading pdf files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     braids
    0.54
     amino
    0.51
     pickles
    0.47
     espuma
    0.47
    ೋನ್
    0.46
     gravel
    0.46
     braid
    0.46
     beaded
    0.46
     limón
    0.46
     queim
    0.46
    POSITIVE LOGITS
     PDF
    1.05
     Acrobat
    0.95
    PDF
    0.92
     Adobe
    0.88
     PDFs
    0.84
     pdf
    0.83
    pdf
    0.82
    Pdf
    0.82
    Adobe
    0.76
     Pdf
    0.75
    Act Density 0.075%

    No Known Activations