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

    Neuronpedia

    INDEX
    Explanations

    programming-related classes and methods, particularly those associated with game mechanics and data handling

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

    The token "class" or words containing "class"

    np_acts-logits-general · gemini-2.0-flash

    programming class references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esternos
    -0.59
     compliance
    -0.54
    :✨
    -0.50
     wireType
    -0.49
     Италијани
    -0.49
    lapsingToolbar
    -0.46
    DockStyle
    -0.44
    Compliance
    -0.43
    compliance
    -0.42
     comply
    -0.41
    POSITIVE LOGITS
    class
    1.04
     class
    0.98
    getClass
    0.71
     classe
    0.70
     clase
    0.66
     Class
    0.65
     getClass
    0.62
     classes
    0.61
     nahilalakip
    0.57
     klasse
    0.56
    Act Density 0.127%

    No Known Activations