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

    Neuronpedia

    INDEX
    Explanations

    lenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fibers
    -0.88
     Cæsar
    -0.77
     ſever
    -0.75
     tires
    -0.73
     pleaſure
    -0.73
     Shakspeare
    -0.72
     ſche
    -0.71
     ſeveral
    -0.71
     itſelf
    -0.70
     Monfieur
    -0.69
    POSITIVE LOGITS
     виправивши
    0.58
    TagMode
    0.56
    Datuak
    0.53
     urgencia
    0.48
     ujednoznacz
    0.47
    imwrite
    0.47
    arned
    0.46
    uploaded
    0.46
    HasForeignKey
    0.45
    ispiele
    0.43
    Act Density 0.027%

    No Known Activations