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

    Neuronpedia

    INDEX
    Explanations

    HR

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of hazard‐related statistics (e.g. “hazard,” “hazard ratios,” “HR”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Hay
    -0.07
    ila
    -0.07
     Dalton
    -0.06
    ẵn
    -0.06
     rays
    -0.06
     clouds
    -0.06
    elay
    -0.06
     menjadi
    -0.06
    olu
    -0.06
    birth
    -0.06
    POSITIVE LOGITS
     stad
    0.07
    ?action
    0.06
     họp
    0.06
     recreation
    0.06
     lider
    0.06
     visible
    0.06
     incred
    0.06
     update
    0.06
    visor
    0.06
     техніч
    0.06
    Act Density 0.003%

    No Known Activations