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

    Neuronpedia

    INDEX
    Explanations

    Chemicals

    np_max-act · gemini-2.0-flash

    The neuron activates on terms naming broad chemical product categories (like pharmaceuticals, agrochemicals, dyes, cosmetics, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    rect
    -0.08
    CEEDED
    -0.07
    _queues
    -0.07
    printStats
    -0.06
    ulado
    -0.06
    "^
    -0.06
     fatigue
    -0.06
    -depth
    -0.06
    uyla
    -0.06
    namespace
    -0.06
    POSITIVE LOGITS
    won
    0.07
     NRL
    0.07
    煤
    0.06
    .divide
    0.06
     demon
    0.06
    ’’
    0.06
     امروز
    0.06
     hometown
    0.06
    .tool
    0.06
    節
    0.06
    Act Density 0.009%

    No Known Activations