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

    Neuronpedia

    INDEX
    Explanations

    mathematical or physics equations containing symbols and units of measure

    oai_token-act-pair · gemini-2.0-flash

    scientific writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.64
    GeneratedMessage
    -0.60
     Waray
    -0.58
    AnimationsModule
    -0.58
     ThemeData
    -0.57
     CURIAM
    -0.57
    Diwedd
    -0.56
    LayoutConstraint
    -0.55
    Superview
    -0.54
    expandindo
    -0.54
    POSITIVE LOGITS
    pausal
    0.57
    发表于
    0.57
     Ambiental
    0.55
    roleum
    0.54
    gento
    0.52
     ergonomics
    0.51
     aérea
    0.50
    }=(
    0.49
    Breakpoint
    0.49
     Rossini
    0.49
    Act Density 3.552%

    No Known Activations