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

    Neuronpedia

    INDEX
    Explanations

    Code and technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     engraçadas
    -0.72
     démocr
    -0.72
     fidèles
    -0.68
     colorés
    -0.66
     africains
    -0.62
     médicaux
    -0.61
     quelcon
    -0.61
     scolaires
    -0.58
     normaux
    -0.58
     financières
    -0.57
    POSITIVE LOGITS
     ProtoMessage
    0.62
    ContentAsync
    0.57
     deep
    0.56
    Geplaatst
    0.54
     profoundly
    0.50
     combineReducers
    0.48
     AssemblyTitle
    0.47
     shortly
    0.47
     deeply
    0.47
     '\\;'
    0.47
    Act Density 0.001%

    No Known Activations