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

    Neuronpedia

    INDEX
    Explanations

    and, comma, period

    np_max-act · gemini-2.0-flash

    discussions about the reliability and purity of words, particularly in a religious or moral context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     apartments
    -0.08
     wonders
    -0.07
    ational
    -0.07
     drawable
    -0.07
     supplier
    -0.07
     controls
    -0.07
     side
    -0.07
    iator
    -0.07
     Society
    -0.07
    }},
    -0.07
    POSITIVE LOGITS
     नद
    0.07
     ⓘ
    0.07
     ح
    0.07
    िसक
    0.06
     istediğiniz
    0.06
    ,.
    0.06
    いか
    0.06
    ुछ
    0.06
    坡
    0.06
     당신
    0.06
    Act Density 0.189%

    No Known Activations