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

    Neuronpedia

    INDEX
    Explanations

    arguments and discussions surrounding ethical considerations in research contexts

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

    arguments and factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.71
    sizeCache
    -0.66
    SharedDtor
    -0.57
     otomatig
    -0.56
     noDo
    -0.54
     &___
    -0.49
    msgTypes
    -0.48
     intStringLen
    -0.47
    tagHelperRunner
    -0.47
     BoxFit
    -0.47
    POSITIVE LOGITS
    SuspendLayout
    0.38
     mainly
    0.38
     regard
    0.36
     environment
    0.35
    Véase
    0.35
     AssemblyProduct
    0.34
     arguments
    0.33
    BeginInit
    0.33
     primarily
    0.32
     réalis
    0.32
    Act Density 0.030%

    No Known Activations