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

    Neuronpedia

    INDEX
    Explanations

    Imper

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.55
     "..\..\
    -0.52
     himo
    -0.50
    ⎨
    -0.50
    urlpatterns
    -0.50
    帖最后由
    -0.49
    router
    -0.47
    PORTS
    -0.47
    LookAnd
    -0.47
     print
    -0.47
    POSITIVE LOGITS
    achella
    0.59
    ſelf
    0.57
    }(),
    0.56
     APD
    0.56
    ēja
    0.54
    kolwiek
    0.54
     passés
    0.53
     automatiques
    0.52
    AOC
    0.52
    issime
    0.50
    Act Density 0.002%

    No Known Activations