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

    Neuronpedia

    INDEX
    Explanations

    formatted output functions and string or formatting operations

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

    Code snippets with colons and punctuation

    np_acts-logits-general · gemini-2.0-flash

    code syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     familiar
    -0.47
     be
    -0.39
    دن
    -0.38
     planches
    -0.38
    /*"
    -0.37
     जान
    -0.37
     big
    -0.37
     It
    -0.36
     komplex
    -0.36
     nhau
    -0.35
    POSITIVE LOGITS
     <>",
    0.96
     disambiguazione
    0.91
    AnimationsModule
    0.90
     "..\..\..\
    0.83
    cèse
    0.82
     <",
    0.81
    ArgsConstructor
    0.80
     initComponents
    0.77
    Viited
    0.75
     "..\..\
    0.72
    Act Density 0.259%

    No Known Activations