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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sell
    -0.07
     Millionen
    -0.07
     другие
    -0.07
    роме
    -0.06
    Numbers
    -0.06
    However
    -0.06
     Converted
    -0.06
    	print
    -0.06
    щих
    -0.06
    Enabled
    -0.06
    POSITIVE LOGITS
     eye
    0.07
    ा
    0.07
    kyně
    0.07
    ii
    0.07
     آذ
    0.06
    activex
    0.06
    ५
    0.06
    2
    0.06
     -‐
    0.06
    iz
    0.06
    Act Density 0.025%

    No Known Activations