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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bserv
    -0.07
    ivalence
    -0.06
     bổ
    -0.06
     řed
    -0.06
     vệ
    -0.06
    igraphy
    -0.06
     plight
    -0.06
     compart
    -0.06
     Kris
    -0.06
     couple
    -0.06
    POSITIVE LOGITS
     countries
    0.09
    Aws
    0.07
    abi
    0.07
     curled
    0.07
     towns
    0.07
    hos
    0.06
     NC
    0.06
    -State
    0.06
     states
    0.06
    .confirm
    0.06
    Act Density 0.011%

    No Known Activations