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

    Neuronpedia

    INDEX
    Explanations

    beverages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lname
    -0.07
     repayment
    -0.07
     knot
    -0.06
    18
    -0.06
     bàn
    -0.06
    462
    -0.06
     지도
    -0.06
     worldly
    -0.06
    ِب
    -0.06
    скільки
    -0.06
    POSITIVE LOGITS
     juice
    0.14
     Juice
    0.12
     juices
    0.11
     juicy
    0.08
    izzling
    0.07
    ]=$
    0.07
    uv
    0.07
     얘
    0.07
    0.07
    ผล
    0.07
    Act Density 0.004%

    No Known Activations