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

    Neuronpedia

    INDEX
    Explanations

    articles/prepositions

    np_max-act · gemini-2.0-flash

    This neuron detects normative and policy‐oriented terms (e.g. responsible, ethical, transparent, monitored) that discuss how AI should be governed or used.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    <Image
    -0.07
     imageSize
    -0.07
     ficken
    -0.06
     Adoles
    -0.06
    paced
    -0.06
     SIGN
    -0.06
     ê
    -0.06
    (IConfiguration
    -0.06
     deniz
    -0.06
     Sweat
    -0.06
    POSITIVE LOGITS
     belly
    0.07
    (limit
    0.07
    =q
    0.07
    -upper
    0.06
    inidad
    0.06
    Okay
    0.06
    /sl
    0.06
    /small
    0.06
     totals
    0.06
    هر
    0.06
    Act Density 0.028%

    No Known Activations