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

    Neuronpedia

    INDEX
    Explanations

    concepts related to legal and contextual terminology

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

    aggravation, deterrence, factor, privacy, respond, substitutution, tasting, transfer, waiver

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.55
     
    -0.46
    1
    -0.42
     Schar
    -0.37
    ba
    -0.36
    A
    -0.36
    2
    -0.36
    3
    -0.35
    5
    -0.35
     A
    -0.34
    POSITIVE LOGITS
    Datuak
    0.93
     propOrder
    0.89
     Reſ
    0.85
    MessageTagHelper
    0.84
     '\\;'
    0.84
     Perſ
    0.82
     pinulongan
    0.81
     ModelExpression
    0.79
    ſelves
    0.79
    abestanden
    0.79
    Act Density 0.235%

    No Known Activations