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

    Neuronpedia

    INDEX
    Explanations

    time references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Strong
    -0.07
    -order
    -0.07
    cribed
    -0.07
     enchant
    -0.07
     institutional
    -0.07
    _results
    -0.06
     energetic
    -0.06
    ood
    -0.06
    _equals
    -0.06
     demanded
    -0.06
    POSITIVE LOGITS
    　　　　　　　　　　　　　
    0.07
     việc
    0.07
     edm
    0.06
    Denver
    0.06
    	client
    0.06
     λειτουργ
    0.06
     تفاوت
    0.06
    MatrixMode
    0.06
     Pets
    0.06
     popup
    0.06
    Act Density 0.015%

    No Known Activations