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

    Neuronpedia

    INDEX
    Explanations

    terms related to candidates and classifications in various contexts

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

    specific technical nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whole
    -0.33
     Wil
    -0.32
     popular
    -0.31
     entire
    -0.31
     proper
    -0.31
    舺
    -0.30
     common
    -0.30
     total
    -0.29
     pure
    -0.29
     copas
    -0.29
    POSITIVE LOGITS
    IUrlHelper
    0.75
    WithIOException
    0.66
    HomeAsUpEnabled
    0.65
     propOrder
    0.60
    featureID
    0.60
    endphp
    0.57
    Espèce
    0.56
    istoitu
    0.56
     Italijanski
    0.55
    SBATCH
    0.54
    Act Density 0.276%

    No Known Activations