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

    Neuronpedia

    INDEX
    Explanations

    comparative statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tagging
    -0.07
     後
    -0.07
     HK
    -0.07
    _reaction
    -0.06
     uk
    -0.06
     fanatic
    -0.06
     Hera
    -0.06
    	header
    -0.06
    920
    -0.06
     ALS
    -0.06
    POSITIVE LOGITS
    uating
    0.07
     nostro
    0.06
    泣
    0.06
     прояв
    0.06
    错
    0.06
    тр
    0.06
    díl
    0.06
     opin
    0.06
    들
    0.06
     направ
    0.06
    Act Density 0.084%

    No Known Activations