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

    Neuronpedia

    INDEX
    Explanations

    file extensions and image formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    0.61
    یت
    0.48
    д
    0.48
    ﺼ
    0.46
    aecat
    0.46
    шей
    0.45
    apter
    0.44
    }}}\
    0.43
    ătoare
    0.43
    atório
    0.42
    POSITIVE LOGITS
     grabs
    0.52
     film
    0.48
    film
    0.47
     filesize
    0.47
     files
    0.46
    tif
    0.46
     convictions
    0.46
     begins
    0.46
    xing
    0.45
     kicks
    0.45
    Act Density 0.001%

    No Known Activations