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

    Neuronpedia

    INDEX
    Explanations

    compens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propagation
    -0.07
    (HWND
    -0.07
     Unknown
    -0.06
    uture
    -0.06
     Ub
    -0.06
     Matching
    -0.06
     insurance
    -0.06
     ubiquitous
    -0.06
     iid
    -0.06
    Split
    -0.06
    POSITIVE LOGITS
    .schema
    0.07
     Filename
    0.07
    PageRoute
    0.07
     Cookie
    0.06
    webdriver
    0.06
    �
    0.06
    _compiler
    0.06
     Leban
    0.06
     conveniently
    0.06
     bubb
    0.06
    Act Density 0.002%

    No Known Activations