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

    Neuronpedia

    INDEX
    Explanations

    references to the classification of items into distinct categories based on their characteristics or roles

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

    "latter" or "former" followed by what they refer to

    np_acts-logits-general · gemini-2.0-flash

    latter, former

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addLine
    -0.36
    MouseListener
    -0.35
     smoking
    -0.33
     Superintendent
    -0.33
    FormTagHelper
    -0.32
     ber
    -0.31
    enderror
    -0.31
     Solicitor
    -0.31
    merie
    -0.31
    KURZBESCHREIBUNG
    -0.31
    POSITIVE LOGITS
     PeEnEo
    0.57
     Савезне
    0.57
     للاسماء
    0.56
     defaultstate
    0.54
     <=",
    0.50
    SharedCtor
    0.49
     leaſt
    0.48
     препратки
    0.47
    OrEqualTo
    0.47
     didst
    0.46
    Act Density 0.743%

    No Known Activations