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

    Neuronpedia

    INDEX
    Explanations

    "as a" role identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     h
    0.66
     Absolute
    0.61
     gill
    0.59
     non
    0.58
     aeg
    0.58
     hue
    0.56
     opposed
    0.56
     tint
    0.56
     "
    0.56
     Buon
    0.55
    POSITIVE LOGITS
     funcionários
    1.15
     desenvolved
    1.11
     разработ
    1.09
     कोरोनावायरस
    1.07
     vimos
    1.07
     organizações
    1.06
    Você
    1.06
     algumas
    1.06
     empresas
    1.04
     escolas
    1.01
    Act Density 0.002%

    No Known Activations