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

    Neuronpedia

    INDEX
    Explanations

    customer-related expressions and sentiments

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

    choices or preferences

    np_acts-logits-general · gemini-2.0-flash

    choice or avoidance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Története
    -0.50
    addCriterion
    -0.45
    garan
    -0.45
     kautta
    -0.44
    Jeografia
    -0.43
    inev
    -0.43
     GlobalKey
    -0.43
    BeginInit
    -0.41
    decode
    -0.41
    localctx
    -0.41
    POSITIVE LOGITS
     prefier
    1.06
     préfère
    1.03
     opted
    0.99
     preferring
    0.98
     prefi
    0.95
     opting
    0.91
     lieber
    0.91
     opt
    0.91
     prefers
    0.90
     avoidance
    0.87
    Act Density 0.247%

    No Known Activations