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

    Neuronpedia

    INDEX
    Explanations

    character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     univers
    -0.06
    äh
    -0.06
     영국
    -0.06
     contenders
    -0.06
    	dist
    -0.06
     стандарт
    -0.06
    盟
    -0.06
     *,
    -0.06
     Ain
    -0.06
     earthly
    -0.06
    POSITIVE LOGITS
     character
    0.07
    plevel
    0.07
     leases
    0.06
     council
    0.06
    Saving
    0.06
    currentUser
    0.06
    ีร
    0.06
     scn
    0.06
     자동차
    0.06
     maxY
    0.06
    Act Density 0.001%

    No Known Activations