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

    Neuronpedia

    INDEX
    Explanations

    research participants

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on methodological and experimental framing phrases (e.g. “The present study,” “Participants,” “Experiment 1,” etc.), i.e. indicators of study design details.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     blockchain
    -0.07
    Fit
    -0.07
     Alexis
    -0.06
     Pv
    -0.06
    opies
    -0.06
     PQ
    -0.06
     FDA
    -0.06
    Explicit
    -0.06
    _exchange
    -0.06
     Ud
    -0.06
    POSITIVE LOGITS
    arden
    0.07
    .entrySet
    0.06
    kee
    0.06
    esti
    0.06
    HideInInspector
    0.06
    corr
    0.06
     indeb
    0.06
    ction
    0.06
    rada
    0.06
    abra
    0.06
    Act Density 0.025%

    No Known Activations