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

    Neuronpedia

    INDEX
    Explanations

    environmental

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of influences or contributing factors (e.g. “influenced by,” “factors including,” “environment,” “culture,” “education,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     notation
    -0.07
    (cmd
    -0.07
     ledge
    -0.06
    utton
    -0.06
    الا
    -0.06
     önüne
    -0.06
     objeto
    -0.06
     expression
    -0.06
     miscar
    -0.06
     Installed
    -0.06
    POSITIVE LOGITS
     منابع
    0.07
    CONTENT
    0.07
     cuz
    0.07
     náv
    0.06
     taj
    0.06
    inyin
    0.06
    َو
    0.06
    賞
    0.06
     UserRepository
    0.06
    Tho
    0.06
    Act Density 0.024%

    No Known Activations