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

    Neuronpedia

    INDEX
    Explanations

    references to various agencies and organizations

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

    news agency, security agency, ad agency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    COLN
    -0.46
     CHF
    -0.44
     Arund
    -0.43
     Wet
    -0.43
    thello
    -0.42
    ''')
    -0.41
     Reversible
    -0.41
    DOC
    -0.41
     EUR
    -0.40
     Northampton
    -0.40
    POSITIVE LOGITS
     agency
    1.02
     agencia
    0.99
     agência
    0.87
     AGENCY
    0.84
    agence
    0.82
     agencias
    0.82
     agence
    0.81
     agencies
    0.80
    Agency
    0.77
     Agency
    0.76
    Act Density 0.004%

    No Known Activations