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

    Neuronpedia

    INDEX
    Explanations

    Problems/issues in online discussion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.98
     ligiloj
    -0.95
     kasarigan
    -0.90
     bonté
    -0.87
     تضيفلها
    -0.85
     autorytatywna
    -0.84
     Efq
    -0.82
     pinulongan
    -0.81
     nahilalakip
    -0.81
     betweenstory
    -0.80
    POSITIVE LOGITS
    .
    0.77
    ,
    0.69
     person
    0.66
     version
    0.65
     pair
    0.65
     épaules
    0.62
     in
    0.60
     chance
    0.57
     way
    0.56
     idea
    0.56
    Act Density 0.210%

    No Known Activations