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

    Neuronpedia

    INDEX
    Explanations

    references to visual art or photography involving children

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

    Depictions of people, especially women and soldiers

    np_acts-logits-general · gemini-2.0-flash

    person holding object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.79
     ویکی‌پدیا
    -0.78
     चीज़ों
    -0.78
     NSCoder
    -0.78
     Houſe
    -0.77
     propOrder
    -0.77
     houſe
    -0.75
    EndInit
    -0.74
     AssemblyCompany
    -0.74
     cauſe
    -0.72
    POSITIVE LOGITS
     pose
    0.93
     smiling
    0.83
     holding
    0.80
     standing
    0.79
     poses
    0.77
     posing
    0.76
     seated
    0.76
     wearing
    0.74
     posed
    0.74
     surrounded
    0.71
    Act Density 0.192%

    No Known Activations