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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ملی
    -0.07
    υπ
    -0.07
    .Asset
    -0.07
     GNU
    -0.07
    lift
    -0.06
     Dallas
    -0.06
    -0.06
     toe
    -0.06
    .canvas
    -0.06
     hry
    -0.06
    POSITIVE LOGITS
    ingleton
    0.06
     még
    0.06
     Unfortunately
    0.06
    ómo
    0.06
     nunca
    0.06
     hyper
    0.06
    .databind
    0.06
    (ARG
    0.06
    Democratic
    0.06
    甚至
    0.06
    Act Density 0.049%

    No Known Activations