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

    Neuronpedia

    INDEX
    Explanations

    flight

    np_max-act · gemini-2.0-flash

    The neuron activates on air‐travel keywords, especially forms of “fly” and “flight.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     CLOCK
    -0.07
    Clock
    -0.07
    leş
    -0.07
    iyel
    -0.06
     亚洲
    -0.06
    zeigt
    -0.06
    .Ui
    -0.06
    collision
    -0.06
     '*'
    -0.06
     kodu
    -0.06
    POSITIVE LOGITS
    !!,
    0.07
    ufe
    0.07
    	Common
    0.06
     cafeteria
    0.06
     Flores
    0.06
     gorge
    0.06
     Scala
    0.06
    ]=[
    0.06
    <
    0.06
     burner
    0.06
    Act Density 0.010%

    No Known Activations