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

    Neuronpedia

    INDEX
    Explanations

    left

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to the phrase “left to” (marking contexts where someone is “left to” do something).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    нош
    -0.07
     favourable
    -0.07
    curve
    -0.07
     pane
    -0.07
     Spiel
    -0.07
    аки
    -0.07
    _win
    -0.07
    odore
    -0.07
     mesure
    -0.07
    awan
    -0.07
    POSITIVE LOGITS
     left
    0.12
    Left
    0.08
     LEFT
    0.08
     Left
    0.08
    left
    0.07
    quared
    0.07
    	left
    0.07
     الو
    0.06
    {EIF
    0.06
    .left
    0.06
    Act Density 0.007%

    No Known Activations