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

    Neuronpedia

    INDEX
    Explanations

    DSM

    np_max-act · gemini-2.0-flash

    The neuron detects references to formal diagnostic manuals and criteria (e.g. “DSM‐5,” “DSM‐IV‐TR,” “criteria,” “Structured Clinical Interview”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    uzz
    -0.07
     needles
    -0.06
    �
    -0.06
    pile
    -0.06
     trigger
    -0.06
    Spark
    -0.06
     Barb
    -0.06
     Owen
    -0.06
     triggers
    -0.06
     Brotherhood
    -0.06
    POSITIVE LOGITS
     Definitions
    0.07
    xcc
    0.07
    точ
    0.06
     enth
    0.06
     interviewed
    0.06
    ся
    0.06
    
    0.06
    τζ
    0.06
     clase
    0.06
     aldığı
    0.06
    Act Density 0.004%

    No Known Activations