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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    terms related to metabolic syndrome and its associations with health conditions.

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

    This neuron activates on numeric tokens containing decimal points (e.g. statistical values, measurements, or probabilities).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     suicide
    -0.07
     Suicide
    -0.07
    (theta
    -0.07
    _sha
    -0.07
    DOB
    -0.07
     signIn
    -0.06
     пох
    -0.06
    ortion
    -0.06
    endsWith
    -0.06
    (det
    -0.06
    POSITIVE LOGITS
    ig
    0.06
     Medi
    0.06
    	Label
    0.06
    Fixed
    0.06
    ware
    0.06
     glad
    0.06
     UIG
    0.06
     seria
    0.06
     Fixed
    0.06
     civilizations
    0.06
    Act Density 0.060%

    No Known Activations