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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming interfaces, classes, and data structures

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

    programming interfaces and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InitVars
    -0.62
    󠁬
    -0.61
    PMailer
    -0.59
     ThemeData
    -0.56
    MemoryWarning
    -0.55
    ⟬
    -0.52
    الحياه
    -0.52
    EndContext
    -0.51
    UnusedPrivate
    -0.51
    AutoField
    -0.50
    POSITIVE LOGITS
    Interface
    0.47
     interface
    0.45
    interface
    0.44
     Interface
    0.41
    Constants
    0.38
     صوتيه
    0.33
    CallBack
    0.33
     Main
    0.33
     interfaces
    0.32
     قابل
    0.32
    Act Density 0.007%

    No Known Activations