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

    Neuronpedia

    INDEX
    Explanations

    references to structures, layers, or examples in procedural or explanatory text

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

    "following" indicates a list or sequence

    np_acts-logits-general · gemini-2.0-flash

    introduces listed items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.66
    writeFieldEnd
    -0.66
    VIAF
    -0.64
     ddelweddau
    -0.63
     lèvres
    -0.62
     AssemblyVersion
    -0.62
    medriver
    -0.62
     voglia
    -0.61
     foncé
    -0.61
     mukana
    -0.61
    POSITIVE LOGITS
     items
    0.80
     two
    0.77
    ⬇️
    0.71
     excerpt
    0.69
     three
    0.68
     additional
    0.67
    maßen
    0.67
     list
    0.66
     scenario
    0.66
     kinds
    0.63
    Act Density 0.220%

    No Known Activations