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

    Neuronpedia

    INDEX
    Explanations

    comments related to ignoring errors in code

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

    try catch blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     annot
    -0.47
    curacy
    -0.46
    toll
    -0.43
     fascin
    -0.42
     excellence
    -0.42
     Acceler
    -0.42
    iscus
    -0.41
    rancy
    -0.41
    uro
    -0.41
    piecze
    -0.41
    POSITIVE LOGITS
    aarrggbb
    0.55
    İstinadlar
    0.47
     utafitiHapana
    0.47
     <<<<<<<<<<<<<<
    0.47
     defaultstate
    0.43
    Forget
    0.41
     forsø
    0.41
    Література
    0.40
     CanadaChoose
    0.39
    UserScript
    0.38
    Act Density 0.004%

    No Known Activations