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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    country
    -0.07
    ･･
    -0.07
     Fell
    -0.06
    温
    -0.06
    zion
    -0.06
    avě
    -0.06
     Sand
    -0.06
     Leah
    -0.06
    Mag
    -0.06
    walk
    -0.06
    POSITIVE LOGITS
     />}↵
    0.06
     anyway
    0.06
     extra
    0.06
    .netty
    0.06
    (gulp
    0.06
     эп
    0.06
     OSI
    0.06
    利
    0.06
    ชร
    0.06
     tiêu
    0.06
    Act Density 0.001%

    No Known Activations