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

    Neuronpedia

    INDEX
    Explanations

    references to awards or recognitions

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

    displaying items

    np_acts-logits-general · gemini-2.0-flash

    hung from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protoimpl
    -0.70
     NSCoder
    -0.68
     propOrder
    -0.68
    RefNanny
    -0.60
    usermodel
    -0.57
    AddTagHelper
    -0.55
    awaiter
    -0.55
    ⋙
    -0.53
    HomeAsUpEnabled
    -0.53
    NameInMap
    -0.53
    POSITIVE LOGITS
     wall
    0.93
     display
    0.85
     murale
    0.76
     installed
    0.76
     hung
    0.74
     hanging
    0.74
     displayed
    0.73
     walls
    0.73
     installation
    0.73
     placed
    0.72
    Act Density 0.154%

    No Known Activations