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

    Neuronpedia

    INDEX
    Explanations

    General sentence structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rior
    -0.08
     muted
    -0.07
    므로
    -0.07
    sessionId
    -0.07
     leží
    -0.07
     мир
    -0.06
     personalised
    -0.06
     enh
    -0.06
     яких
    -0.06
    род
    -0.06
    POSITIVE LOGITS
     arrested
    0.07
    一个
    0.06
    격
    0.06
    TestMethod
    0.06
    449
    0.06
    Π
    0.06
     日本
    0.06
     ips
    0.06
     Wikimedia
    0.06
     Mitgli
    0.05
    Act Density 0.001%

    No Known Activations