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

    Neuronpedia

    INDEX
    Explanations

    the conjunction "and" in various contexts

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

    connecting two items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.52
     EconPapers
    -0.45
    等
    -0.43
     BAH
    -0.40
     etc
    -0.40
     needs
    -0.40
     we
    -0.39
     bulk
    -0.39
    grande
    -0.38
     happy
    -0.38
    POSITIVE LOGITS
     виправивши
    0.59
    ⓧ
    0.58
    RenderAtEndOf
    0.56
    canestro
    0.53
    GOTREF
    0.52
    ImageContext
    0.49
    ✨:
    0.48
     transfieras
    0.48
    <?
    0.46
    EndContext
    0.46
    Act Density 0.034%

    No Known Activations