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

    Neuronpedia

    INDEX
    Explanations

    technical terms and structured data formats

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

    Characters often found in code snippets

    np_acts-logits-general · gemini-2.0-flash

    contract information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlType
    -0.58
    DockStyle
    -0.54
     argento
    -0.48
    GeneratedValue
    -0.47
     distanciation
    -0.47
    fxml
    -0.47
     Algorithm
    -0.46
    voor
    -0.45
    antee
    -0.45
    createServer
    -0.44
    POSITIVE LOGITS
     gas
    0.84
     Gas
    0.74
    gas
    0.74
    Gas
    0.72
     Contract
    0.70
    ergies
    0.67
    CONTRACT
    0.67
    Contract
    0.66
    contract
    0.65
     contract
    0.64
    Act Density 0.074%

    No Known Activations