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

    Neuronpedia

    INDEX
    Explanations

    reference markers in scientific contexts, particularly figures or tables

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

    bracketed references, equations, and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.45
    parsedMessage
    -1.32
    RegressionTest
    -1.23
     MainAxisSize
    -1.20
    majánló
    -1.15
    ſicht
    -1.12
    iſchen
    -1.11
     témoig
    -1.11
    WriteTagHelper
    -1.10
    UnitTesting
    -1.10
    POSITIVE LOGITS
            
    0.52
    0.50
        
    0.50
                
    0.49
    <code>
    0.49
    0.47
    0.46
          
    0.46
    1
    0.45
    <td>
    0.45
    Act Density 0.004%

    No Known Activations