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

    Neuronpedia

    INDEX
    Explanations

    specific programming syntax and structures, particularly in object-oriented programming and functional programming contexts

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

    Characters often found inside parentheses/brackets

    np_acts-logits-general · gemini-2.0-flash

    code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    بوابة
    -0.58
    WriteBarrier
    -0.53
     '+':
    -0.53
     saites
    -0.51
    contentLoaded
    -0.51
    ismet
    -0.50
    ázat
    -0.48
     PackageManager
    -0.48
     ujednoznacz
    -0.47
    انيف
    -0.47
    POSITIVE LOGITS
     item
    0.93
     x
    0.75
    item
    0.72
    x
    0.60
     ITEM
    0.58
     entity
    0.58
     i
    0.57
     p
    0.56
     element
    0.56
     Item
    0.54
    Act Density 0.616%

    No Known Activations