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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oncé
    -0.07
    landers
    -0.07
    -pad
    -0.07
    anned
    -0.06
    graph
    -0.06
    GitHub
    -0.06
     Review
    -0.06
    Backup
    -0.06
    cookie
    -0.06
     NSA
    -0.06
    POSITIVE LOGITS
     LocalDate
    0.07
     NGX
    0.07
     �
    0.06
     altar
    0.06
    <>(
    0.06
     primaryStage
    0.06
    comings
    0.06
    .jsoup
    0.06
    危
    0.06
     jewish
    0.06
    Act Density 0.031%

    No Known Activations