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

    Neuronpedia

    INDEX
    Explanations

    informal online discourse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     railway
    -0.08
    .follow
    -0.07
     Design
    -0.07
     Geography
    -0.07
     upp
    -0.07
     Arr
    -0.07
     Over
    -0.07
     "-
    -0.07
     policeman
    -0.06
     migration
    -0.06
    POSITIVE LOGITS
    ใด
    0.07
    ikut
    0.07
     삼
    0.07
    ті
    0.06
    "urls
    0.06
    مي
    0.06
    _maps
    0.06
     страш
    0.06
    _SAN
    0.06
    رج
    0.06
    Act Density 0.325%

    No Known Activations