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
     TypeError
    -0.07
    <ActionResult
    -0.06
     Formatting
    -0.06
     cosmetics
    -0.06
    의
    -0.06
     Proceedings
    -0.06
     calibrated
    -0.06
    erosis
    -0.06
    Tower
    -0.06
    质量
    -0.06
    POSITIVE LOGITS
     person
    0.06
    ерш
    0.06
    .Env
    0.06
     Dost
    0.06
     Fem
    0.06
     Appalachian
    0.06
     nab
    0.06
    arts
    0.05
     си
    0.05
     defa
    0.05
    Act Density 0.014%

    No Known Activations