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

    Neuronpedia

    INDEX
    Explanations

    programming constructs that indicate conditional logic or variable definitions

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

    code structure initiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.75
    IContainer
    -0.59
    SourceChecksum
    -0.58
     <=",
    -0.56
    RetentionPolicy
    -0.52
    tagext
    -0.51
    expandindo
    -0.51
    
    -0.50
    WaitGroup
    -0.50
     Biôgrafia
    -0.50
    POSITIVE LOGITS
     Plan
    0.44
    Plan
    0.44
     Plant
    0.42
     bề
    0.41
    ConverterFactory
    0.41
     Slat
    0.40
     fabbrica
    0.40
    PLANT
    0.39
     diensten
    0.39
    contentLoaded
    0.39
    Act Density 0.015%

    No Known Activations