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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =context
    -0.09
    Transparency
    -0.08
    sandbox
    -0.08
    透明
    -0.08
     confidential
    -0.08
     symbolic
    -0.08
    Acl
    -0.08
     transparency
    -0.08
    	context
    -0.08
    acl
    -0.08
    POSITIVE LOGITS
     선수
    0.09
     كرة
    0.09
     football
    0.09
     Talent
    0.08
     गेंद
    0.08
     Fußball
    0.08
    球
    0.08
    ionato
    0.08
     Charger
    0.08
     Rapids
    0.08
    Act Density 0.038%

    No Known Activations