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

    Neuronpedia

    INDEX
    Explanations

    every

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onaut
    -0.06
     leaks
    -0.06
    wear
    -0.06
     Lev
    -0.06
     настоя
    -0.06
     DATA
    -0.06
    _receipt
    -0.06
     trace
    -0.06
    452
    -0.06
    올
    -0.06
    POSITIVE LOGITS
     humor
    0.07
    iswa
    0.07
    -law
    0.06
     conjug
    0.06
     Kashmir
    0.06
    ReturnType
    0.06
    -building
    0.06
     dari
    0.06
     pubb
    0.06
    uso
    0.06
    Act Density 0.001%

    No Known Activations