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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مشين
    -0.75
     defaultstate
    -0.74
     виправивши
    -0.69
    expandindo
    -0.66
     Italijani
    -0.64
     насељу
    -0.63
     незавершена
    -0.61
     beginnetje
    -0.59
    disposing
    -0.59
    DeleteBehavior
    -0.59
    POSITIVE LOGITS
    twimg
    0.50
     contained
    0.49
    出版年
    0.48
    itinéraire
    0.46
    koku
    0.45
    RegressionTest
    0.43
    Migration
    0.42
     found
    0.41
    word
    0.41
    ud
    0.41
    Act Density 0.008%

    No Known Activations