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

    Neuronpedia

    INDEX
    Explanations

    risk management

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens specifying quantitative trading risk controls—especially position-sizing, stop-loss, and risk-management parameters.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _subtype
    -0.07
     Litecoin
    -0.06
     созда
    -0.06
     storefront
    -0.06
     Sherman
    -0.06
     XF
    -0.06
    -themed
    -0.06
     Raqqa
    -0.06
     Scient
    -0.06
     Af
    -0.05
    POSITIVE LOGITS
    table
    0.07
     Ca
    0.07
    /her
    0.06
    います
    0.06
    ubber
    0.06
    ћ
    0.06
     fostering
    0.06
    čin
    0.06
    those
    0.06
     Digit
    0.06
    Act Density 0.014%

    No Known Activations