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

    Neuronpedia

    INDEX
    Explanations

    Order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	AL
    -0.07
    007
    -0.07
     baik
    -0.07
    悠
    -0.07
    ipline
    -0.06
     Countries
    -0.06
     Fu
    -0.06
     Xi
    -0.06
    oling
    -0.06
     effortless
    -0.06
    POSITIVE LOGITS
    ').
    0.07
    _visitor
    0.07
     Stripe
    0.06
    /connect
    0.06
    umbnail
    0.06
    	new
    0.06
     refunds
    0.06
     novo
    0.06
    .ng
    0.06
    [array
    0.06
    Act Density 0.089%

    No Known Activations