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

    Neuronpedia

    INDEX
    Explanations

    braces and their nested structures within code

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

    Code snippets or code-related text

    np_acts-logits-general · gemini-2.0-flash

    proof of lemmas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AllAfrica
    -0.54
     surla
    -0.54
    /
    -0.53
    aternion
    -0.53
    '];?>
    -0.50
    tvguidetime
    -0.50
    borderSide
    -0.49
    IntoConstraints
    -0.48
    termilk
    -0.48
    省市镇
    -0.48
    POSITIVE LOGITS
     idéia
    0.63
    JsonHelper
    0.62
     Exactly
    0.58
     intellectuelle
    0.58
    Hauptartikel
    0.58
    __':
    0.57
     prochaines
    0.56
    __":
    0.55
    )\}$
    0.55
    OGND
    0.54
    Act Density 0.143%

    No Known Activations