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

    Neuronpedia

    INDEX
    Explanations

    max min

    np_max-act · gemini-2.0-flash

    The neuron is specialized to spot occurrences of the “max” operation (e.g. the token “max”) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ウ
    -0.07
     timetable
    -0.06
     разом
    -0.06
    Ult
    -0.06
     Paleo
    -0.06
    。今
    -0.06
    Tele
    -0.06
     تقویت
    -0.06
    ời
    -0.06
     polit
    -0.06
    POSITIVE LOGITS
     Aggregate
    0.07
     sponsored
    0.07
     aggregate
    0.07
    (Vector
    0.07
    ponsored
    0.06
    _maps
    0.06
    _NODES
    0.06
     predicates
    0.06
     potentials
    0.06
     mains
    0.06
    Act Density 0.005%

    No Known Activations