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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    chemical compounds and their synthesis processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects complex chemical compound names marked by numeric locants and hyphens (e.g. “7-Hydroxy-1,2,3,4-tetrahydroquinoline”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ูน
    -0.07
    ********************************************************
    -0.07
    /cpu
    -0.07
     chips
    -0.06
     theolog
    -0.06
    “You
    -0.06
    >)
    -0.06
     запит
    -0.06
    ยก
    -0.06
     chip
    -0.06
    POSITIVE LOGITS
    -display
    0.07
     atIndex
    0.07
    (contents
    0.07
    ceiving
    0.06
    ตร
    0.06
    (Activity
    0.06
    .cur
    0.06
    .Details
    0.06
    disciplinary
    0.06
    ceive
    0.06
    Act Density 0.017%

    No Known Activations