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

    Neuronpedia

    INDEX
    Explanations

    references to IP addresses

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

    citations and footnotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verrez
    -0.50
    <bos>
    -0.48
     Hogar
    -0.47
    ymce
    -0.47
     industriel
    -0.47
     contactez
    -0.46
     femeninos
    -0.46
     religieux
    -0.46
     bancaire
    -0.46
     commerciaux
    -0.46
    POSITIVE LOGITS
    ]:
    1.73
    ]]:
    1.20
     ]:
    1.14
    "]:
    1.02
    ']:
    1.02
    ]:
    0.98
    :]:
    0.92
    >:
    0.91
    )]:
    0.90
    ])):
    0.86
    Act Density 0.007%

    No Known Activations