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

    Neuronpedia

    INDEX
    Explanations

    service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inse
    -0.06
    macen
    -0.06
    .="
    -0.06
     accidents
    -0.06
     departments
    -0.06
    Fort
    -0.06
     prostřed
    -0.06
     sparkle
    -0.06
     atm
    -0.06
    pear
    -0.05
    POSITIVE LOGITS
     ++)
    0.07
     UserController
    0.07
    miner
    0.06
    cry
    0.06
     변수
    0.06
    .getBytes
    0.06
    كو
    0.06
    umbo
    0.06
    폰
    0.06
     youthful
    0.06
    Act Density 0.004%

    No Known Activations