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

    Neuronpedia

    INDEX
    Explanations

    LaTeX image and drawing code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    paragraph
    0.78
    dish
    0.76
    eland
    0.76
    ifend
    0.71
    ood
    0.70
    date
    0.70
    etal
    0.70
    emarks
    0.69
    rfloor
    0.69
    mark
    0.67
    POSITIVE LOGITS
    includegraphics
    1.00
     pictured
    0.95
     portray
    0.92
     pasting
    0.92
     includ
    0.91
     including
    0.90
     portrays
    0.89
     Picture
    0.89
     obraz
    0.88
     Includes
    0.86
    Act Density 0.001%

    No Known Activations