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

    Neuronpedia

    INDEX
    Explanations

    sentiments related to government policies and their impact on the economy

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

    wrong prescription/tax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     although
    -0.35
    although
    -0.34
     Milne
    -0.32
    ніципалі
    -0.31
    mainly
    -0.31
     particular
    -0.31
     aunque
    -0.31
    anmoins
    -0.30
     hitherto
    -0.30
     Хотя
    -0.30
    POSITIVE LOGITS
     Jefus
    0.74
    :✨
    0.66
     Anſ
    0.65
     Verſ
    0.63
     myſelf
    0.61
     leaſt
    0.60
     HasFactory
    0.59
    omitempty
    0.59
     pleaſure
    0.59
     occaf
    0.59
    Act Density 0.047%

    No Known Activations