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

    Neuronpedia

    INDEX
    Explanations

    chemical compounds, medical research

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of drug metabolite names or structural fragments (e.g. “9-hydroxy,” “desmethyl,” “nor-,” “N-oxide”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ρίς
    -0.06
     Multip
    -0.06
    =============↵
    -0.06
     vur
    -0.06
    .packet
    -0.06
    _contrib
    -0.06
     Oaks
    -0.06
     //!
    -0.06
    _predict
    -0.06
     uploader
    -0.05
    POSITIVE LOGITS
     Rem
    0.07
    nave
    0.07
    kinson
    0.07
    平台
    0.06
     succession
    0.06
     learnt
    0.06
    Assistant
    0.06
    leaning
    0.06
     leaning
    0.06
     caller
    0.06
    Act Density 0.016%

    No Known Activations