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

    Neuronpedia

    INDEX
    Explanations

    code structures and syntax related to programming, particularly function definitions and return statements

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

    return, attach, register, initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.63
     nahilalakip
    -0.57
    matchCondition
    -0.56
    RegistryLite
    -0.52
    MarshalTo
    -0.50
    SharedDtor
    -0.48
    awtextra
    -0.48
     AspNetCore
    -0.45
     désolés
    -0.44
    المكان
    -0.43
    POSITIVE LOGITS
     registering
    0.50
     attach
    0.48
     attaching
    0.47
     등록
    0.47
     attached
    0.47
     registration
    0.46
     register
    0.45
     Initial
    0.44
     attaches
    0.44
     initializing
    0.44
    Act Density 0.035%

    No Known Activations