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

    Neuronpedia

    INDEX
    Explanations

    key mathematical symbols and terms used in analytical discussions

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

    Bifrost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PeEnEo
    -0.76
    -0.73
    ConstraintMaker
    -0.73
    aarrggbb
    -0.67
    enderror
    -0.65
    MLLoader
    -0.63
    IndentedString
    -0.63
    httphttps
    -0.63
     pinulongan
    -0.62
    astify
    -0.61
    POSITIVE LOGITS
    źć
    0.34
    <h2>
    0.32
    ________________
    0.30
    的一
    0.28
    </h2>
    0.28
    ————————————————
    0.28
    目前
    0.27
    <strong>
    0.26
    antMatchers
    0.26
    ----------------
    0.26
    Act Density 0.029%

    No Known Activations