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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (typ
    -0.06
     Kids
    -0.06
     completely
    -0.06
    (selector
    -0.06
     struct
    -0.06
     primitives
    -0.06
    (sem
    -0.06
     getMenuInflater
    -0.06
     lazy
    -0.06
    -new
    -0.06
    POSITIVE LOGITS
    moth
    0.07
    quito
    0.06
     hastalık
    0.06
    ﻟ
    0.06
    ﺮ
    0.06
    ponsor
    0.06
    CKET
    0.06
    sey
    0.06
    тер
    0.06
    (CG
    0.06
    Act Density 0.096%

    No Known Activations