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

    Neuronpedia

    INDEX
    Explanations

    due

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on language about assumed consent—specifically the phrase “assume consent is granted.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     เซ
    -0.07
     soils
    -0.07
    (*)
    -0.07
    oned
    -0.06
    名字
    -0.06
     jsonObj
    -0.06
     Σα
    -0.06
     redistributed
    -0.06
    /buttons
    -0.06
    ('?
    -0.06
    POSITIVE LOGITS
    套
    0.07
    	layout
    0.07
     estamos
    0.07
     asthma
    0.06
     backdrop
    0.06
    density
    0.06
     waterfall
    0.06
     Damn
    0.06
    prov
    0.06
     Riy
    0.06
    Act Density 0.002%

    No Known Activations