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

    Neuronpedia

    INDEX
    Explanations

    differences and classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    server
    0.52
    new
    0.49
    device
    0.47
    io
    0.46
    files
    0.45
    software
    0.45
    data
    0.44
    export
    0.43
    open
    0.43
    storage
    0.43
    POSITIVE LOGITS
     preferencias
    0.77
     perbedaan
    0.77
     ethnicity
    0.76
     diferenças
    0.75
     differences
    0.73
     diferencias
    0.70
     preferências
    0.70
    差异
    0.69
     différences
    0.69
     Unterschiede
    0.69
    Act Density 2.686%

    No Known Activations