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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liabilities
    -0.06
     UNICODE
    -0.06
    rick
    -0.06
     instability
    -0.06
     Dota
    -0.06
     Asset
    -0.06
    cribes
    -0.06
     Opens
    -0.06
    mayı
    -0.06
    ksiyon
    -0.06
    POSITIVE LOGITS
     feu
    0.07
     هند
    0.06
    	holder
    0.06
     canned
    0.06
     są
    0.06
     대한민국
    0.05
     Hon
    0.05
    	sql
    0.05
     được
    0.05
     %{
    0.05
    Act Density 0.009%

    No Known Activations