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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash

    This neuron activates on descriptions of an academic study’s methods and administrative details—especially phrases about the study being conducted or approved (e.g. “the study was approved by…”), participant enrollment, and related procedural statements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ignoring
    -0.07
    	stream
    -0.07
    ESTAMP
    -0.06
     sediment
    -0.06
    .GetKey
    -0.06
     loads
    -0.06
    .subscribe
    -0.06
    널
    -0.06
     kitchen
    -0.06
     kings
    -0.06
    POSITIVE LOGITS
     เช
    0.07
     Importance
    0.07
    余
    0.06
    zig
    0.06
    igrate
    0.06
     waist
    0.06
    _crypto
    0.06
    '],'
    0.06
     جنسی
    0.06
     sia
    0.06
    Act Density 0.003%

    No Known Activations