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

    Neuronpedia

    INDEX
    Explanations

    Twin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Photos
    -0.06
    ่าว
    -0.06
     فیلم
    -0.06
    ấm
    -0.06
     Month
    -0.06
     mundo
    -0.06
     Cart
    -0.06
    ocha
    -0.06
    Cart
    -0.06
    人的
    -0.06
    POSITIVE LOGITS
     Twin
    0.10
     Twins
    0.08
    win
    0.08
     twins
    0.07
     twin
    0.07
     Partner
    0.07
    Brun
    0.07
     leo
    0.07
    WIN
    0.07
    타
    0.07
    Act Density 0.002%

    No Known Activations