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

    Neuronpedia

    INDEX
    Explanations

    code-related constructs and function calls involving string and message handling

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

    Code, often with "add" and string manipulation

    np_acts-logits-general · gemini-2.0-flash

    add text to string

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.02
     defaultstate
    -0.94
     дописавши
    -0.94
     propOrder
    -0.90
    Autoritní
    -0.89
    fjspx
    -0.88
    setVerticalGroup
    -0.88
    ftagPool
    -0.87
     otomatig
    -0.84
     BoxFit
    -0.83
    POSITIVE LOGITS
    новременно
    0.52
     plus
    0.50
     Plus
    0.46
     
    0.45
    plus
    0.44
    спу
    0.43
     потом
    0.42
     drop
    0.41
     -
    0.41
     point
    0.41
    Act Density 0.562%

    No Known Activations