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

    Neuronpedia

    INDEX
    Explanations

    conditional statements in programming code

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

    Code snippets, often after assignment or definition

    np_acts-logits-general · gemini-2.0-flash

    direct value access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.97
    TagMode
    -0.92
    awtextra
    -0.89
     typelib
    -0.86
    httphttps
    -0.86
    resizingMask
    -0.85
    脚注の使い方
    -0.85
     Paglinawan
    -0.83
    rungsseite
    -0.83
     jScrollPane
    -0.81
    POSITIVE LOGITS
     simply
    0.74
    simply
    0.56
     просто
    0.56
     simplemente
    0.55
     itself
    0.54
    <eos>
    0.51
     merely
    0.50
     simplesmente
    0.50
     directly
    0.48
     semplicemente
    0.48
    Act Density 0.203%

    No Known Activations