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

    Neuronpedia

    INDEX
    Explanations

    instances of entries and actions related to data structures or programming operations

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

    code punctuation endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.57
    >",
    -0.56
     <=",
    -0.52
     propOrder
    -0.51
    Rüyada
    -0.50
    ('../../../
    -0.50
     queſta
    -0.49
    期刊论文
    -0.49
    AnchorStyles
    -0.47
     garcía
    -0.47
    POSITIVE LOGITS
     productivo
    0.36
    MLLoader
    0.35
    RepeatedField
    0.33
     rück
    0.31
     muchacho
    0.30
     취
    0.29
     new
    0.29
     cadeia
    0.29
    ikä
    0.29
     abgerufen
    0.28
    Act Density 0.004%

    No Known Activations