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

    Neuronpedia

    INDEX
    Explanations

    code snippets and programming jargon

    oai_token-act-pair · gemini-2.0-flash

    code/math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.76
     = 
    -0.70
     ſtate
    -0.69
     Jefus
    -0.69
     ſta
    -0.68
     Majefty
    -0.68
     leſs
    -0.67
     themſelves
    -0.66
     ſhe
    -0.66
     leaſt
    -0.66
    POSITIVE LOGITS
    WebVitals
    0.77
    LookAnd
    0.73
    GenerationType
    0.60
     "..\..\..\
    0.54
     "..\..\
    0.51
    oredCriteria
    0.50
     BrowserModule
    0.50
    TintMode
    0.50
     snippetHide
    0.49
     '\\;'
    0.48
    Act Density 39.124%

    No Known Activations