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

    Neuronpedia

    INDEX
    Explanations

    elements of programming code related to variable definitions and assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets and mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    boolean literals and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -}
    -0.89
     -,
    -0.83
     /
    -0.80
     =
    -0.75
     ?",
    -0.74
     <<
    -0.74
     =",
    -0.72
     ?',
    -0.72
    "]);
    -0.72
     ...]
    -0.72
    POSITIVE LOGITS
    kháu
    0.87
    ,(
    0.80
     AssemblyCulture
    0.77
    =
    0.75
    ArrowToggle
    0.73
    ==
    0.71
    (()=>{
    0.71
    GEBURTSDATUM
    0.70
    encodeWith
    0.70
     میتوان
    0.70
    Act Density 3.194%

    No Known Activations