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
    ?page
    -0.07
    antas
    -0.06
    awesome
    -0.06
    washer
    -0.06
    #ab
    -0.06
     Layout
    -0.06
    -0.06
     आकर
    -0.06
     اولین
    -0.06
     ویر
    -0.06
    POSITIVE LOGITS
     gec
    0.07
     Gray
    0.06
     Weld
    0.06
    dik
    0.06
     volunteers
    0.06
     Elliot
    0.06
     оказ
    0.06
    Ệ
    0.06
    ,[
    0.06
     Ens
    0.06
    Act Density 0.013%

    No Known Activations