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

    Neuronpedia

    INDEX
    Explanations

    width or height or apps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unov
    0.46
     silicone
    0.45
     cowboy
    0.44
     songs
    0.44
     exemplify
    0.44
     nonstop
    0.44
     seorang
    0.43
     aerobic
    0.43
    imple
    0.43
     evolved
    0.43
    POSITIVE LOGITS
    Helping
    0.44
    Menus
    0.43
     Respublik
    0.42
    确实
    0.41
    Household
    0.41
    sche
    0.40
    মুক্ত
    0.40
     якія
    0.40
    ι
    0.40
    hazardous
    0.40
    Act Density 0.001%

    No Known Activations