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

    Neuronpedia

    INDEX
    Explanations

    instances of exceptions or conditions in a method or process

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

    except to the extent that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noDo
    -0.51
    SharedCtor
    -0.50
    tableFuture
    -0.50
    AccessorTable
    -0.49
    queryInterface
    -0.48
     useAppContext
    -0.48
    __':
    -0.47
     InputDecoration
    -0.47
    TagMode
    -0.47
    SocketChannel
    -0.47
    POSITIVE LOGITS
     Climbing
    0.40
    Doing
    0.39
    Running
    0.39
    Rules
    0.39
     vent
    0.38
    testify
    0.38
    inon
    0.38
     skip
    0.37
     lean
    0.37
     begin
    0.37
    Act Density 0.000%

    No Known Activations