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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash

    The neuron is triggered by month names when they appear as part of date expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ecs
    -0.07
     bios
    -0.06
     passenger
    -0.06
     Tau
    -0.06
     medium
    -0.06
    FAILURE
    -0.06
     Fischer
    -0.06
    Std
    -0.06
     throttle
    -0.06
     comparison
    -0.06
    POSITIVE LOGITS
    џџџџџџџџџџџџџџџџ
    0.07
     กรกฎาคม
    0.07
    २०
    0.07
    사회
    0.07
     зависит
    0.07
     इतन
    0.07
    โลย
    0.07
     生命周期函数
    0.06
     активно
    0.06
     обычно
    0.06
    Act Density 0.004%

    No Known Activations