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

    Neuronpedia

    INDEX
    Explanations

    One

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     himself
    -0.07
    emony
    -0.06
     yourself
    -0.06
    aa
    -0.06
     GNU
    -0.06
     Calvin
    -0.06
     herself
    -0.06
     Squ
    -0.06
     arbitrarily
    -0.06
     ourselves
    -0.06
    POSITIVE LOGITS
     One
    0.07
    公里
    0.07
     estados
    0.07
     경기도
    0.06
     преп
    0.06
     خام
    0.06
    اید
    0.06
     λεπ
    0.06
    SEC
    0.06
    -feira
    0.06
    Act Density 0.038%

    No Known Activations