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

    Neuronpedia

    INDEX
    Explanations

    symmetry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     errone
    -0.07
     Separ
    -0.06
     Aston
    -0.06
    仕
    -0.06
    최신
    -0.06
     Wendy
    -0.06
     sociology
    -0.06
     Armor
    -0.06
    needed
    -0.06
     tercih
    -0.06
    POSITIVE LOGITS
     exciting
    0.07
     프로그램
    0.06
     pans
    0.06
     witnessed
    0.06
    чить
    0.06
     пат
    0.06
    ину
    0.06
    244
    0.06
    _used
    0.06
    inctions
    0.06
    Act Density 0.009%

    No Known Activations