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

    Neuronpedia

    INDEX
    Explanations

    statements and quotations from individuals or sources

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

    Attribution or direct quote

    np_acts-logits-general · gemini-2.0-flash

    speaker attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.78
    StructEnd
    -0.75
     فريبيس
    -0.70
    IsContent
    -0.67
    featureID
    -0.64
     wikipagina
    -0.63
    +#+#
    -0.63
     betweenstory
    -0.63
     yourselves
    -0.63
    spender
    -0.62
    POSITIVE LOGITS
     kasarigan
    0.71
    })`
    0.70
    ')],
    0.67
    )"),
    0.65
    ]]:
    0.64
    ++]=
    0.64
    ))));
    0.63
     spokeswoman
    0.62
    ())),
    0.62
    ">',
    0.62
    Act Density 0.134%

    No Known Activations