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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Versions
    -0.08
    断
    -0.07
     ups
    -0.06
    uve
    -0.06
    eb
    -0.06
    ricao
    -0.06
     inds
    -0.06
    rails
    -0.06
     sigue
    -0.06
     scan
    -0.06
    POSITIVE LOGITS
    .Quantity
    0.09
    	column
    0.07
    ΥΣ
    0.07
     Steelers
    0.07
     Cisco
    0.06
    -client
    0.06
    (New
    0.06
    	cin
    0.06
    ст
    0.06
    .drag
    0.06
    Act Density 0.002%

    No Known Activations