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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and control flow constructs in programming

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

    Code that contains "if (" statements

    np_acts-logits-general · gemini-2.0-flash

    conditional checks and assertions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.92
     متعلقه
    -0.90
     myſelf
    -0.86
     ujednoznacz
    -0.85
    WithIOException
    -0.85
     arşivlendi
    -0.80
    numerusform
    -0.79
     AssemblyProduct
    -0.79
     iſt
    -0.78
    ſelves
    -0.77
    POSITIVE LOGITS
     in
    0.64
    empty
    0.60
     empty
    0.59
    isset
    0.56
    ,
    0.55
     is
    0.53
     class
    0.53
    !
    0.53
     
    0.52
     count
    0.50
    Act Density 0.057%

    No Known Activations