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

    Neuronpedia

    INDEX
    Explanations

    words related to code and programming in languages other than English

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BrowserModule
    -0.80
     CommonModule
    -0.78
     '\\;'
    -0.74
    RenderAtEndOf
    -0.73
    OGND
    -0.70
    protoimpl
    -0.63
    InjectAttribute
    -0.57
     дописавши
    -0.56
     EClass
    -0.56
    */)
    -0.53
    POSITIVE LOGITS
     définiti
    0.79
     élevées
    0.74
     supérieurs
    0.73
     intermédiaire
    0.70
     fermés
    0.69
     élevés
    0.69
     courants
    0.68
     pédagog
    0.68
     fédé
    0.66
     normaux
    0.66
    Act Density 3.411%

    No Known Activations